IBM at NeurIPS 2022

Description:

Partially monotone regression is a regression analysis in which the target values are monotonically increasing with respect to a subset of input features. The TensorFlow Lattice library is one of the standard machine learning libraries for partially monotone regression. It consists of several neural network layers, and its core component is the lattice layer. One of the problems of the lattice layer is its requirement for a special training algorithm to satisfy monotonicity constraints. Another problem is that it cannot receive a high-dimensional input vector due to the resultant memory consumption. We propose a novel neural network layer, the hierarchical lattice layer (HLL), as an extension of the lattice layer so that we can use a standard neural network algorithm to train HLL while satisfying monotonicity constraints and so that it can receive a high-dimensional input vector. Our experiments demonstrate that HLL did not sacrifice its prediction performance on real datasets compared with the lattice layer.

Hiroki Yanagisawa (IBM); Kohei Miyaguchi (IBM); Takayuki Katsuki (IBM)

Description:

The mixing time of the Markov chain induced by a policy limits performance in real-world continual learning scenarios. Yet, the effect of mixing times on learning in continual reinforcement learning (RL) remains underexplored. In this paper, we characterize problems that are of long-term interest to the development of continual RL, which we call scalable MDPs, through the lens of mixing times. In particular, we theoretically establish that scalable MDPs have mixing times that scale polynomially with the size of the problem. We go on to demonstrate that polynomial mixing times present significant difficulties for existing approaches that suffer from myopic bias and stale bootstrapped estimates. To validate the proposed theory, we study the empirical scaling behavior of mixing times with respect to the number of tasks and task switching frequency for pretrained high performing policies on seven Atari games. Our analysis demonstrates both that polynomial mixing times do emerge in practice and how their existence may lead to unstable learning behavior like catastrophic forgetting in continual learning settings.

Matthew Riemer (IBM); Sharath Raparthy; Ignacio Cases; Gopeshh Subbaraj; Maximilian Touzel; Irina Rish

Description:

Foundation Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, as we show in this paper, FMs still have poor out-of-the-box performance on expert tasks (e.g. retrieval of car manuals technical illustrations from language queries), data for which is either unseen or belonging to a long-tail part of the data distribution of the huge datasets used for FM pre-training. This underlines the necessity to explicitly evaluate and finetune FMs on such expert tasks, arguably ones that appear the most in practical real-world applications. In this paper, we propose a first of its kind FETA benchmark built around the task of teaching FMs to understand technical documentation, via learning to match their graphical illustrations to corresponding language descriptions. Our FETA benchmark focuses on text-to-image and image-to-text retrieval in public car manuals and sales catalogue brochures. FETA is equipped with a procedure for completely automatic annotation extraction (code would be released upon acceptance), allowing easy extension of FETA to more documentation types and application domains in the future. Our automatic annotation leads to an automated performance metric shown to be consistent with metrics computed on human-curated annotations (also released). We provide multiple baselines and analysis of popular FMs on FETA leading to several interesting findings that we believe would be very valuable to the FM community, paving the way towards real-world application of FMs for practical expert tasks currently 'overlooked' by standard benchmarks focusing on common objects.

Amit Alfassy (IBM); Assaf Arbelle (IBM); Oshri Halimi; Sivan Harary (IBM); Roi Herzig; Eliyahu Schwartz (IBM); Rameswar Panda (IBM); Michele Dolfi (IBM); Christoph Auer (IBM); Peter Staar (IBM); Kate Saenko (IBM); Rogerio Feris (IBM); Leonid Karlinsky

Description:

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment’s transition and reward dynamics. An effective approach that has recently emerged for addressing this non-stationarity is for each agent to anticipate the learning of other agents and influence the evolution of future policies towards desirable behavior for its own benefit. Unfortunately, previous approaches for achieving this suffer from myopic evaluation, considering only a finite number of policy updates. As such, these methods can only influence transient future policies rather than achieving the promise of scalable equilibrium selection approaches that influence the behavior at convergence. In this paper, we propose a principled framework for considering the limiting policies of other agents as time approaches infinity. Specifically, we develop a new optimization objective that maximizes each agent’s average reward by directly accounting for the impact of its behavior on the limiting set of policies that other agents will converge to. Our paper characterizes desirable solution concepts within this problem setting and provides practical approaches for optimizing over possible outcomes. As a result of our farsighted objective, we demonstrate better long-term performance than state-of-the-art baselines across a suite of diverse multiagent benchmark domains.

Dong Ki Kim; Matthew Riemer (IBM); Miao Liu (IBM); Jakob Foerster; Michael Everret; Chuangchuang Sun; Gerald Tesauro (IBM); Jonathan How

Description:

Most of the existing algorithms for zero-shot classification problems typically rely on the attribute-based semantic relations among categories to realize the classification of novel categories without observing any of their instances. However, training the zero-shot classification models still requires attribute labeling for each class (or even instance) in the training dataset, which is also expensive. To this end, in this paper, we bring up a new problem scenario: ''Can we derive zero-shot learning for novel attribute detectors/classifiers and use them to automatically annotate the dataset for labeling efficiency?'' Basically, given only a small set of detectors that are learned to recognize some manually annotated attributes (i.e., the seen attributes), we aim to synthesize the detectors of novel attributes in a zero-shot learning manner. Our proposed method, Zero-Shot Learning for Attributes (ZSLA), which is the first of its kind to the best of our knowledge, tackles this new research problem by applying the set operations to first decompose the seen attributes into their basic attributes and then recombine these basic attributes into the novel ones. Extensive experiments are conducted to verify the capacity of our synthesized detectors for accurately capturing the semantics of the novel attributes and show their superior performance in terms of detection and localization compared to other baseline approaches. Moreover, we demonstrate the application of automatic annotation using our synthesized detectors on Caltech-UCSD Birds-200-2011 dataset. Various generalized zero-shot classification algorithms trained upon the dataset re-annotated by ZSLA shows comparable performance with those trained with the manual ground-truth annotations.

Yu-hsuan Li; Tzu-yin Chao; Ching-chun Huang; Pin-Yu Chen (IBM); Wei-Chen Chiu

Description:

A classical result of Johnson and Lindenstrauss states that a set of n high dimensional data points can be projected down to O(log n/ε^2) dimensions such that the square of their pairwise distances will be preserved up to some small distortion ε ∈ (0,1). This work aims to improve this1/ε^2 dependency based on techniques inspired by the Hutch++ Algorithm [23], which, remarkably, reduced1/ε^2 to1/ε for the related problem of implicit matrix trace estimation. Forε = 0.01, for example, this translates to 100 times less matrix-vector products in the matrix-vector query model to achieve the same accuracy. We first present an algorithm for estimating the Euclidean lengths of the rows of a matrix for which we prove (i) element-wise probabilistic bounds which are at least as good as standard JL estimations in the worst case, but are asymptotically better for matrices with rapidly decaying spectrum and (ii) for any matrix, regardless its spectrum, the algorithm can achieve εaccuracy for the total, Frobenius norm-wise relative error using only O(1/ε) queries, which is a quadratic improvement over standard JL approximations. We show that these results can also be extended for two other important problems, namely for estimating the Euclidean distances between data points, as well as for approximating the statistical leverage scores of a tall-and-skinny data matrix. We also provide indicative numerical experiments validating our theoretical analysis.

Aleksandros Sobczyk (IBM); Mathieu Luisier

Description:

Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. In addition, finding the optimal hyper-parameter configuration, even with state-of-the-art (SOTA) hyper-parameter optimization (HPO) algorithms, can be time-consuming, requiring multiple training runs over the entire dataset for different possible sets of hyper-parameters. Our central insight is that using an informative subset of the dataset for model training runs involved in hyper-parameter optimization, allows us to find the optimal hyper-parameter configuration significantly faster. In this work, we propose AUTOMATA, a gradient-based subset selection framework for hyper-parameter tuning. We empirically evaluate the effectiveness of AUTOMATA in hyper-parameter tuning through several experiments on real-world datasets in the text, vision, and tabular domains. Our experiments show that using gradient-based data subsets for hyper-parameter tuning achieves significantly faster turnaround times and speedups of 3-30 while achieving comparable performance to the hyper-parameters found using the entire dataset.

Krishnateja Killamsetty; Guttu Sai Abhishek; Aakriti Lnu; Alexandre Evfimievski (IBM); Lucian Popa (IBM); Ganesh Ramakrishnan; Rishabh Iyer

Description:

We consider the task of training machine learning models with data-dependent constraints. Such constraints often arise as empirical versions of expected value constraints that enforce fairness or stability goals. We reformulate data-dependent constraints so that they are \emph{calibrated}: enforcing the reformulated constraints guarantees that their expected value counterparts are satisfied with a user-prescribed probability. The resulting optimization problem is amendable to standard stochastic optimization algorithms, and we demonstrate the efficacy of our method on a fairness-sensitive classification task where we wish to guarantee the classifier's fairness (at test time).

Songkai Xue; Yuekai Sun; Mikhail Yurochkin (IBM)

Description:

In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive attributes such as race and gender is one key intervention to strive for equity. Focusing on demographic parity and equality of opportunity, in this paper we propose an algorithm that improves the fairness of a pre-trained classifier by simply dropping carefully selected training data points. We select instances based on their influence on the fairness metric of interest, computed using an infinitesimal jackknife-based approach. The dropping of training points is done in principle, but in practice does not require the model to be refit. Crucially, we find that such an intervention does not substantially reduce the predictive performance of the model but drastically improves the fairness metric. Through careful experiments, we evaluate the effectiveness of the proposed approach on diverse tasks and find that it consistently improves upon existing alternatives.

Prasanna Sattigeri (IBM); Soumya Ghosh (IBM); Inkit Padhi (IBM); Pierre Dognin (IBM); Kush Varshney (IBM)

Description:

Action recognition has improved dramatically with massive-scale video datasets. Yet, these datasets are accompanied with issues related to curation cost, privacy, ethics, bias, and copyright. Compared to that, only minor efforts have been devoted toward exploring the potential of synthetic video data. In this work, as a stepping stone towards addressing these shortcomings, we study the transferability of video representations learned solely from synthetically-generated video clips, instead of real data. We propose SynAPT, a novel benchmark for action recognition based on a combination of existing synthetic datasets, in which a model is pre-trained on synthetic videos rendered by various graphics simulators, and then transferred to a set of downstream action recognition datasets, containing different categories than the synthetic data. We provide an extensive baseline analysis on SynAPT revealing that the simulation-to-real gap is minor for datasets with low object and scene bias, where models pre-trained with synthetic data even outperform their real data counterparts. We posit that the gap between real and synthetic action representations can be attributed to contextual bias and static objects related to the action, instead of the temporal dynamics of the action itself.

Yo-whan Kim; Samarth Mishra (IBM); Souyoung Jin; Rameswar Panda (IBM); Hildegard Kuehne; Leonid Karlinsky (IBM); Kate Saenko (IBM); Aude Oliva; Rogerio Feris (IBM)

Description:

We propose VRL3, a powerful data-driven framework with a minimalist design for solving highly challenging visual deep reinforcement learning (DRL) tasks. We analyze a number of major obstacles in taking a data-driven approach, and present a suite of design principles, novel findings, and critical insights about data-driven visual DRL. Our framework has three stages: in stage 1, we leverage non-RL datasets (e.g. ImageNet) to learn task-agnostic visual representations; in stage 2, we use offline RL data (e.g. a limited number of expert demonstrations) to convert the task-agnostic representations into more powerful task-specific representations; in stage 3, we fine-tune the agent with online RL. On a set of highly challenging hand manipulation tasks with sparse reward and realistic visual inputs, compared to the previous SOTA, VRL3 achieves an average of 780% better sample efficiency. And on the hardest task, VRL3 is 1220% more sample efficient and solves the task with only 10% of the computation. These highly significant results clearly demonstrate the great potential of data-driven deep reinforcement learning.

Che Wang; Xufang Luo; Keith Ross; Dongsheng Li (IBM)

Description:

We study the following independence testing problem: given access to samples from a distribution P over ${0,1}^n$, decide whether P is a product distribution or whether it is ε-far in total variation distance from any product distribution. For arbitrary distributions, this problem requires exp(n) samples. We show in this work that if P has a sparse structure, then in fact only linearly many samples are required.Specifically, if P is Markov with respect to a Bayesian network whose underlying DAG has in-degree bounded by d, then ~Θ( $2^{d/2}$ ⋅n/ $ε^2$) samples are necessary and sufficient for independence testing.

Arnab Bhattacharyya; Clément Cannone (IBM); Qiping Yang

Description:

Graph-level anomaly detection aims to distinguish anomalous graphs in a graph dataset from normal graphs. Anomalous graphs represent very few but essential patterns in the real world. The anomalous property of a graph may be referable to its anomalous attributes of particular nodes and anomalous substructures referring to a subset of nodes and edges in the graph. In addition, due to the imbalance nature of anomaly problem, the anomalous information will be diluted by normal graphs with overwhelming quantities. Various anomaly notions in the attributes and/or substructures and the imbalance nature together make detecting anomalous graphs a non-trivial task. In this paper, we propose a dual-discriminative graph neural network for graph-level anomaly detection, namely iGAD. Specifically, an anomalous graph attribute-aware graph convolution and an anomalous graph substructure-aware deep Random Walk Kernel (deep RWK) are welded into a graph neural network to achieve a dual-discriminative ability on anomalous attributes and substructures. The deep RWK in iGAD makes up for the deficiency of graph convolution in distinguishing structural information caused by the simple neighborhood aggregation mechanism. Further, we propose a Point Mutual Information-based loss function to address the imbalance nature of anomaly problem. The loss function enables iGAD to capture the essential correlation between input graphs and their anomalous/normal properties. We evaluate iGAD on four real-world graph datasets. Extensive experiments demonstrate the superiority of iGAD on the graph-level anomaly detection task.

Ge Zhang; Zhenyu Yang; Jia Wu; Jian Yang; Shan Xue; Hao Peng; Jianlin Su; Chuan Zhou; Quan Z. Sheng; Leman Akoglu; Charu Aggarwal (IBM)

Description:

The deployment constraints in practical applications necessitate the pruning of large-scale deep learning models, i.e., promoting their weight sparsity. As illustrated by the Lottery Ticket Hypothesis (LTH), pruning also has the potential of improving their generalization ability. At the core of LTH, iterative magnitude pruning (IMP) is the predominant pruning method to successfully find ‘winning tickets’. Yet, the computation cost of IMP grows prohibitively as the targeted pruning ratio increases. To reduce the computation overhead, various efficient ‘one-shot’ pruning methods have been developed, but these schemes are usually unable to find winning tickets as good as IMP. This raises the question of how to close the gap between pruning accuracy and pruning efficiency? To tackle it, we pursue the algorithmic advancement of model pruning. Specifically, we formulate the pruning problem from a fresh and novel viewpoint, bi-level optimization (BLO). We show that the BLO interpretation provides a technically-grounded optimization base for an efficient implementation of the pruning-retraining learning paradigm used in IMP. We also show that the proposed bi-level optimization-oriented pruning method (termed BiP) is a special class of BLO problems with a bi-linear problem structure. By leveraging such bi-linearity, we theoretically show that BiP can be solved as easily as first-order optimization, thus inheriting the computation efficiency. Through extensive experiments on both structured and unstructured pruning with 5 model architectures and 4 data sets, we demonstrate that BiP can find better winning tickets than IMP in most cases, and is computationally as efficient as the one-shot pruning schemes, demonstrating 2-7x speedup over IMP for the same level of model accuracy and sparsity.

Yihua Zhang; Yuguang Yao; Parikshit Ram (IBM); Pu Zhao; Tianlong Chen; Mingyi Hong; Yanzhi Wang; Sijia Liu (IBM)

Description:

Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods have been developed, they are computationally expensive and scale poorly with respect to both dataset and network complexity. Widespread usage of certified training is further hindered by the fact that periodic retraining is necessary to incorporate new data and network improvements. In this paper, we propose Certified Robustness Transfer (CRT), a general-purpose framework for reducing the computational overhead of any certifiably robust training method through knowledge transfer. Given a robust teacher, our framework uses a novel training loss to transfer the teacher's robustness to the student. We provide theoretical and empirical validation of CRT. Our experiments on CIFAR-10 show that CRT speeds up certified robustness training by 8x on average across three different architecture generations, while achieving comparable robustness to state-of-the-art methods. We also show that CRT can scale to large-scale datasets like ImageNet.

Pratik Vaishnavi; Kevin Eykholt (IBM); Amir Rahmati

Description:

We consider the problem of robustly testing the norm of a high-dimensional sparse signal vector under two different observation models. In the first model, we are given n i.i.d. samples from the distribution N(θ, $I\_d$ ) (with unknown θ), of which a small fraction has been arbitrarily corrupted. Under the promise that ∥θ∥0≤s, we want to correctly distinguish whether ∥θ∥ $\_2$ =0 or ∥θ∥ $\_2$ >γ, for some input parameter γ>0. We show that any algorithm for this task requires n=Ω(s log ed/s) samples, which is tight up to logarithmic factors. We also extend our results to other common notions of sparsity, namely, ∥θ∥q≤s for any 0<q<2. In the second observation model that we consider, the data is generated according to a sparse linear regression model, where the covariates are i.i.d. Gaussian and the regression coefficient (signal) is known to be s-sparse. Here too we assume that an ϵ-fraction of the data is arbitrarily corrupted. We show that any algorithm that reliably tests the norm of the regression coefficient requires at least n=Ω(min(s log d,1/γ4)) samples. Our results show that the complexity of testing in these two settings significantly increases under robustness constraints. This is in line with the recent observations made in robust mean testing and robust covariance testing.

Anand Jerry George; Clément Cannone

Description:

Our environment is filled with rich and dynamic acoustic information. When we walk into a cathedral, the reverberations as much as appearance inform us of the sanctuary's wide open space. Similarly, as an object moves around us, we expect the sound emitted to also exhibit this movement. While recent advances in learned implicit functions have led to increasingly higher quality representations of the visual world, there have not been commensurate advances in learning spatial auditory representations. To address this gap, we introduce Neural Acoustic Fields (NAFs), an implicit representation that captures how sounds propagate in a physical scene. By modeling acoustic propagation in a scene as a linear time-invariant system, NAFs learn to continuously map all emitter and listener location pairs to a neural impulse response function that can then be applied to arbitrary sounds. We demonstrate that the continuous nature of NAFs enables us to render spatial acoustics for a listener at an arbitrary location, and can predict sound propagation at novel locations. We further show that the representation learned by NAFs can help improve visual learning with sparse views. Finally, we show that a representation informative of scene structure emerges during the learning of NAFs.

Andrew Luo; Yilun Du; Michael J. Tarr; Josh Tenenbaum; Antonio Torralba; Chuang Gan (IBM)

Description:

Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between safety and interpretability more quantitative. Toward assessing safety, we introduce the concept of \emph{maximum deviation} via an optimization problem to find the largest deviation of a supervised learning model from a reference model regarded as safe. We then show how interpretability facilitates this safety assessment. For models including decision trees, generalized linear and additive models, the maximum deviation can be computed exactly and efficiently. For tree ensembles, which are not regarded as interpretable, discrete optimization techniques can still provide informative bounds. For a broader class of piecewise Lipschitz functions, we leverage the multi-armed bandit literature to show that interpretability produces tighter (regret) bounds on the maximum deviation. We present case studies, including one on mortgage approval, to illustrate our methods and the insights about models that may be obtained from deviation maximization.

Dennis Wei (IBM); Rahul Nair (IBM); Amit Dhurandhar (IBM); Kush Varshney (IBM); Elizabeth Daly (IBM); Moninder Singh (IBM)

Description:

Pre-trained transformer models have achieved remarkable success in natural language processing (NLP) and have recently become competitive alternatives to Convolution Neural Networks (CNN) and Recurrent Neural Networks (RNN) in vision and speech tasks, respectively. Due to excellent computational efficiency and scalability, transformer models can be trained on exceedingly large amounts of data; however, model sizes can grow tremendously. As high performance, large-scale, and pre-trained transformer models become available for users to download and fine-tune for customized downstream tasks, the deployment of these models becomes challenging due to the vast amount of operations and large memory footprint. To address this challenge, we introduce methods to deeply compress pre-trained transformer models across three major application domains: NLP, speech, and vision. Specifically, we quantize transformer backbones down to 4-bit and further achieve 50% fine-grained structural sparsity on pre-trained BERT, Wav2vec2.0 and Vision Transformer (ViT) models to achieve 16x compression while maintaining model accuracy. This is achieved by identifying the critical initialization for quantization/sparsity aware fine-tuning, as well as novel techniques including quantizers with zero-preserving format and scheduled drop-out. These hardware-friendly techniques need only to be applied in the fine-tuning phase for downstream tasks; hence, are especially suitable for acceleration and deployment of pre-trained transformer models.

Naigang Wang (IBM); Charlie Liu (IBM); Swagath Venkataramani (IBM); Sanchari Sen (IBM); Chia-Yu Chen (IBM); Kaoutar El Maghraoui (IBM); Vijayalakshmi Srinivasan (IBM); Leland Chang (IBM)

Description:

Contemporary deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For example, it is hard to study the robustness of these networks to variations of object scale, object pose, scene lighting and 3D occlusions. The main reason is that collecting real datasets with fine-grained naturalistic variations can be extremely time-consuming and expensive. In this work, we present Counterfactual Simulation Testing, a counterfactual framework that allows us to study the robustness of neural networks with respect to some of these naturalistic variations by building realistic synthetic scenes that allow us to ask counterfactual questions to the models, ultimately providing answers to questions such as "Would your classification still be correct if the object were viewed from the top?" or "Would your classification still be correct if the object would be partially occluded by another object?". Our method allows for a fair comparison of the robustness of recently released, state-of-the-art Convolutional Neural Networks and Vision Transformers, with respect to these naturalistic variations. We find evidence that ConvNext is more robust to pose and scale variations than Swin, that ConvNext generalizes better to our simulated domain and that Swin handles partial occlusion better than ConvNext. We also find that robustness for all networks improves with network scale and with data scale and variety.

Nataniel Ruiz; Cihang Xie; Sarah Bargal; Kate Saenko (IBM); Stan Sclaroff

Description:

On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model. However, the training memory consumption is prohibitive for IoT devices that have tiny memory resources. We propose an algorithm-system co-design framework to make on-device training possible with only 256KB of memory. On-device training faces two unique challenges: (1) the quantized graphs of neural networks are hard to optimize due to mixed bit-precision and the lack of normalization; (2) the limited hardware resource (memory and computation) does not allow full backward computation. To cope with the optimization difficulty, we propose Quantization-Aware Scaling to calibrate the gradient scales and stabilize quantized training. To reduce the memory footprint, we propose Sparse Update to skip the gradient computation of less important layers and sub-tensors. The algorithm innovation is implemented by a lightweight training system, Tiny Training Engine, which prunes the backward computation graph to support sparse updates and offloads the runtime auto-differentiation to compile time. Our framework is the first practical solution for on-device transfer learning of visual recognition on tiny IoT devices (e.g., a microcontroller with only 256KB SRAM), using less than 1/100 of the memory of existing frameworks while matching the accuracy of cloud training+edge deployment for the tinyML application VWW. Our study enables IoT devices to not only perform inference but also continuously adapt to new data for on-device lifelong learning.

Ji Lin; Ligeng Zhu; Wei-ming Chen; Wei-chen Wang; Chuang Gan (IBM); Song Han

Description:

Meta learning has demonstrated tremendous success in few-shot learning with limited supervised data. In those settings, the meta model is usually overparameterized. While the conventional statistical learning theory suggests that overparameterized models tend to overfit, empirical evidence reveals that overparameterized meta learning methods still work well - a phenomenon often called benign overfitting.'' In an attempt to understand this phenomenon, we focus on the meta learning settings with a challenging bilevel structure that we term the gradient-based meta learning, and analyze its generalization performance under an overparameterized meta linear regression model. While our analysis uses the relatively tractable linear models, our theory contributes to understanding the delicate interplay among data heterogeneity, model adaptation and benign overfitting in gradient-based meta learning tasks. We corroborate our theoretical claims through numerical simulations.

Lisha Chen; Songtao Lu (IBM); Tianyi Chen

Description:

We introduce Logical Credal Networks (or LCNs for short) -- an expressive probabilistic logic that generalizes prior formalisms that combine logic and probability. Given imprecise information represented by probability bounds and conditional probability bounds on logic formulas, an LCN specifies a set of probability distributions over all its interpretations. Our approach allows propositional and first-order logic formulas with few restrictions, e.g., without requiring acyclicity. We also define a generalized Markov condition that allows us to identify implicit independence relations between atomic formulas. We evaluate our method on benchmark problems such as random networks, Mastermind games with uncertainty and credit card fraud detection. Our results show that the LCN outperforms existing approaches; its advantage lies in aggregating multiple sources of imprecise information.

Radu Marinescu (IBM); Haifeng Qian; Alexander Gray (IBM); Debarun Bhattacharjya (IBM); Francisco Barahona (IBM); Tian Gao (IBM); Ryan Riegel (IBM); Pravinda Sahu (IBM)

Description:

Spectral clustering is popular among practitioners and theoreticians alike. While performance guarantees for spectral clustering are well understood, recent studies have focused on enforcing ``fairness'' in clusters, requiring them to be ``balanced'' with respect to a categorical sensitive node attribute (e.g. the race distribution in clusters must match the race distribution in the population). In this paper, we consider a setting where sensitive attributes indirectly manifest in an auxiliary \textit{representation graph} rather than being directly observed. This graph specifies node pairs that can represent each other with respect to sensitive attributes and is observed in addition to the usual \textit{similarity graph}. Our goal is to find clusters in the similarity graph while respecting a new individual-level fairness constraint encoded by the representation graph. We develop variants of unnormalized and normalized spectral clustering for this task and analyze their performance under a \emph{fair} planted partition model induced by the representation graph. This model uses both the cluster membership of the nodes and the structure of the representation graph to generate random similarity graphs. To the best of our knowledge, these are the first consistency results for constrained spectral clustering under an individual-level fairness constraint. Numerical results corroborate our theoretical findings.

Shubham Gupta (IBM); Ambedkar Dukkipati

Description:

Existing gradient-based optimization methods update the parameters locally, in a direction that minimizes the loss function. We study a different approach, symmetry teleportation, that allows the parameters to travel a large distance on the loss level set, in order to improve the convergence speed in subsequent steps. Teleportation exploits parameter space symmetries of the optimization problem and transforms parameters while keeping the loss invariant. We derive the loss-invariant group actions for test functions and multi-layer neural networks, and prove a necessary condition of when teleportation improves convergence rate. We also show that our algorithm is closely related to second order methods. Experimentally, we show that teleportation improves the convergence speed of gradient descent and AdaGrad for several optimization problems including test functions, multi-layer regressions, and MNIST classification.

Bo Zhao; Nima Dehmamy (IBM); Robin Walters; Rose Yu

Description:

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of generative processes which are hard to integrate together to scale up. To overcome this, we propose training with a large dataset of twenty-one thousand programs, each one generating a diverse set of synthetic images. These programs are short code snippets, which are easy to modify and fast to execute using OpenGL. The proposed dataset can be used for both supervised and unsupervised representation learning, and reduces the gap between pre-training with real and procedurally generated images by 38%.

Manel Baradad; Richard Chen; Jonas Wulff; Tongzhou Wang; Rogerio Feris (IBM); Antonio Torralba; Phillip Isola

Description:

Humans have a remarkable ability to rapidly generalize to new tasks that is difficult to reproduce in artificial learning systems.Compositionality has been proposed as a key mechanism supporting generalization in humans, but evidence of its neural implementation and impact on behavior is still scarce. Here we study the computational properties associated with compositional generalization in both humans and artificial neural networks (ANNs) on a highly compositional task. First, we identified behavioral signatures of compositional generalization in humans, along with their neural correlates using whole-cortex functional magnetic resonance imaging (fMRI) data. Next, we designed pretraining paradigms aided by a procedure we term primitives pretraining to endow compositional task elements into ANNs. We found that ANNs with this prior knowledge had greater correspondence with human behavior and neural compositional signatures. Importantly, primitives pretraining induced abstract internal representations, excellent zero-shot generalization, and sample-efficient learning. Moreover, it gave rise to a hierarchy of abstract representations that matched human fMRI data, where sensory rule abstractions emerged in early sensory areas, and motor rule abstractions emerged in later motor areas. Our findings give empirical support to the role of compositional generalization in humans behavior, implicate abstract representations as its neural implementation, and illustrate that these representations can be embedded into ANNs by designing simple and efficient pretraining procedures.

Takuya Ito; Tim Klinger (IBM); Douglas Schultz; John D. Murray; Michael Cole; Mattia Rigotti

Description:

Federated learning (FL) faces challenges of intermittent client availability and computation/communication efficiency. As a result, only a small subset of clients can participate in FL at a given time. It is important to understand how partial client participation affects convergence, but most existing works have either considered idealized participation patterns or obtained results with non-zero optimality error for generic patterns. In this paper, we provide a unified convergence analysis for FL with arbitrary client participation. We first introduce a generalized version of federated averaging (FedAvg) that amplifies parameter updates at an interval of multiple FL rounds. Then, we present a novel analysis that captures the effect of client participation in a single term. By analyzing this term, we obtain convergence upper bounds for a wide range of participation patterns, including both non-stochastic and stochastic cases, which match either the lower bound of stochastic gradient descent (SGD) or the state-of-the-art results in specific settings. We also discuss various insights, recommendations, and experimental results.

Shiqiang Wang (IBM); Mingyue Ji

Description:

Dealing with non-stationarity in environments (i.e., transition dynamics) and objectives (i.e., reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most current approaches model the changes as a single shared embedding vector, we leverage insights from the recent causality literature to model non-stationarity in terms of individual latent change factors and causal graphs across different environments. In particular, we propose Factored Adaptation for Non-Stationary RL (FANS-RL), a factored adaption approach that learns jointly the causal structure in terms of a factored MDP, and a factored representation of the individual time-varying change factors. We prove that under standard assumptions we can recover completely the causal graph representing the factored transition and reward function, and a partial structure between the individual change factors and the state components. Through our general framework, we can consider general non-stationary scenarios with different changing function types and changing frequency, including changes across episodes and within episodes. Experimental results demonstrate that FANS-RL outperforms existing approaches in terms of rewards, compactness of the latent state representation and robustness to varying degrees of non-stationarity.

Fan Feng; Biwei Huang; Kun Zhang; Sara Magliacane (IBM)

Description:

Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases. In particular, we show that (i) enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models under the covariate shift assumption and that (ii) it is possible to adapt representation alignment methods for domain adaptation to enforce individual fairness. The former is unexpected because IF interventions were not developed with distribution shifts in mind. The latter is also unexpected because representation alignment is not a common approach in the individual fairness literature.

Debarghya Mukherjee; Felix Petersen; Mikhail Yurochkin (IBM); Yuekai Sun

Description:

Self-supervised learning (SSL) for rich speech representations has achieved empirical success in low-resource Automatic Speech Recognition (ASR) and other speech processing tasks, which can mitigate the necessity of a large amount of transcribed speech and thus has driven a growing demand for on-device ASR and other speech processing. However, advanced speech SSL models have become increasingly large, which contradicts the limited on-device resources. This gap could be more severe in multilingual/multitask scenarios requiring simultaneously recognizing multiple languages or executing multiple speech processing tasks. Additionally, strongly overparameterized speech SSL models tend to suffer from overfitting when being finetuned on low-resource speech corpus. This work aims to enhance the practical usage of speech SSL models towards a win-win in both enhanced efficiency and alleviated overfitting via our proposed S$^3$-Router framework, which for the first time discovers that simply discarding no more than 10\% of model weights via only finetuning model connections of speech SSL models can achieve better accuracy over standard weight finetuning on downstream speech processing tasks. More importantly, S$^3$-Router can serve as an all-in-one technique to enable (1) a new finetuning scheme, (2) an efficient multilingual/multitask solution, (3) a state-of-the-art pruning technique, and (4) a new tool to quantitatively analyze the learned speech representation.

Yonggan Fu; Yang Zhang (IBM); Kaizhi Qian (IBM); Zhifan Ye; Cheng-I Lai; Yingyan Lin

Description:

Most people associate the term `hedging' exclusively with financial applications, particularly the use of financial derivatives. We argue that hedging is an activity that human and machine agents should engage in more broadly, even when the agent's value is not necessarily in monetary units. In this paper, we propose a decision-theoretic view of hedging based on augmenting a probabilistic graphical model -- specifically a Bayesian network or an influence diagram -- with a reward. Hedging is therefore posed as a particular kind of graph manipulation, and can be viewed as analogous to control/intervention and information gathering related analysis. Effective hedging occurs when a risk-averse agent finds opportunity to balance uncertain rewards in their current situation. We illustrate the concepts with examples and counter-examples, and conduct experiments to demonstrate the properties and applicability of the proposed computational tools that enable agents to proactively identify potential hedging opportunities in real-world situations.

Debarun Bhattacharjya (IBM); Radu Marinescu (IBM)

Description:

We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions often contain descriptions of objects in the environment and path cues defined by humans. To achieve accurate and efficient navigation, it is critical to build a map that accurately represents both spatial location and the semantic information of the environment objects. However, enabling a robot to build a map that well represents the environment is extremely challenging as the environment often involves diverse objects with various attributes. In this paper, we propose a multi-granularity map, which contains both object fine-grained details (eg, color, texture) and semantic classes, to represent objects more comprehensively. Moreover, we propose a weakly-supervised auxiliary task, which requires the agent to localize instruction-relevant objects on the map. Through this task, the agent not only learns to localize the instruction-relevant objects for navigation but also is encouraged to learn a better map representation that reveals object information. We then feed the learned map and instruction to a waypoint predictor to determine the next navigation goal. Experimental results show our method outperforms the state-of-the-art by 4.0% and 4.6% w.r.t. success rate both in seen and unseen environments, respectively on VLN-CE dataset.

Peihao Chen; Dongyu Ji; Kunyang Lin; Runhao Zeng; Thomas Li; Mingkui Tan; Chuang Gan (IBM)

Description:

Traditional analyses in non-convex optimization typically rely on the smoothness assumption, namely requiring the gradients to be Lipschitz. However, recent evidence shows that this smoothness condition does not capture the properties of some deep learning objective functions, including the ones involving Recurrent Neural Networks and LSTMs. Instead, they satisfy a much more relaxed condition, with potentially unbounded smoothness. Under this relaxed assumption, it has been theoretically and empirically shown that the gradient-clipped SGD has an advantage over the vanilla one. In this paper, we show that clipping is not indispensable for Adam-type algorithms in tackling such scenarios: we theoretically prove that a generalized SignSGD algorithm can obtain similar convergence rates as SGD with clipping but does not need explicit clipping at all. This family of algorithms on one end recovers SignSGD and on the other end closely resembles the popular Adam algorithm. Our analysis underlines the critical role that momentum plays in analyzing SignSGD-type and Adam-type algorithms: it not only reduces the effects of noise, thus removing the need for large mini-batch in previous analyses of SignSGD-type algorithms, but it also substantially reduces the effects of unbounded smoothness and gradient norms. We also compare these algorithms with popular optimizers on a set of deep learning tasks, observing that we can match the performance of Adam while beating the others.

Michael Crawshaw; Mingrui Liu; Francesco Orabona; Wei Zhang (IBM); Zhenxun Zhuang

Description:

Sentence scoring aims at measuring the likelihood score of a sentence and is widely used in many natural language processing scenarios, like reranking, which is to select the best sentence from multiple candidates. Previous works on sentence scoring mainly adopted either causal language modeling (CLM) like GPT or masked language modeling (MLM) like BERT, which have some limitations: 1) CLM only utilizes unidirectional information for the probability estimation of a sentence without considering bidirectional context, which affects the scoring quality; 2) MLM can only estimate the probability of partial tokens at a time and thus requires multiple forward passes to estimate the probability of the whole sentence, which incurs large computation and time cost. In this paper, we propose \textit{Transcormer} -- a Transformer model with a novel \textit{sliding language modeling} (SLM) for sentence scoring. Specifically, our SLM adopts a triple-stream self-attention mechanism to estimate the probability of all tokens in a sentence with bidirectional context and only requires a single forward pass. SLM can avoid the limitations of CLM (only unidirectional context) and MLM (multiple forward passes) and inherit their advantages, and thus achieve high effectiveness and efficiency in scoring. Experimental results on multiple tasks demonstrate that our method achieves better performance than other language modelings.

Kaitao Song; Yichong Leng; Xu Tan; Yicheng Zou; Tao Qin; Dongsheng Li (IBM)

Description:

Similarity search in graph databases is one of the most fundamental operations in graph analytics. Among various distance functions, graph and subgraph edit distances (GED and SED respectively) are two of the most popular and expressive measures. Unfortunately, exact computations for both are NP-hard. To overcome this computational bottleneck, neural approaches to learn and predict edit distance in polynomial time have received much interest. While considerable progress has been made, there exist limitations that need to be addressed. First, the efficacy of an approximate distance function lies not only in its approximation accuracy, but also in the preservation of its properties. To elaborate, although GED is a metric, its neural approximations do not provide such a guarantee. This prohibits their usage in higher order tasks that rely on metric distance functions, such as clustering or indexing. Second, several existing frameworks for GED do not extend to SED due to SED being asymmetric. In this work, we design a novel siamese graph neural network called Greed, which through a carefully crafted inductive bias, learns GED and SED in a property-preserving manner. Through extensive experiments across real graph datasets containing up to million edges, we establish that Greed is not only more accurate than the state of the art, but also up to orders of magnitude faster. Even more significantly, due to preserving the triangle inequality, the generated embeddings are indexable and consequently, even in a CPU-only environment, Greed is up to times faster than GPU-powered computations of the closest baseline.

Rishab Ranjan; Siddharth Grover; Sourav Medya; Venkatesan Chakravarthy (IBM); Yogish Sabharwal; Sayan Ranu

Description:

There have been multiple works that try to ascertain explanations for decisions of black box models on particular inputs by perturbing the input or by sampling around it, creating a neighborhood and then fitting a sparse (linear) model (e.g. LIME). Many of these methods are unstable and so more recent work tries to find stable or robust alternatives. However, stable solutions may not accurately represent the behavior of the model around the input. Thus, the question we ask in this paper is are we approximating the local boundary around the input accurately? In particular, are we sampling the right neighborhood so that a linear approximation of the black box is faithful to its true behavior around that input given that the black box can be highly non-linear (viz. deep relu network with many linear pieces). It is difficult to know the correct neighborhood width (or radius) as too small a width can lead to a bad condition number of the inverse covariance matrix of function fitting procedures resulting in unstable predictions, while too large a width may lead to accounting for multiple linear pieces and consequently a poor local approximation. We in this paper propose a simple approach that is robust across neighborhood widths in recovering faithful local explanations. In addition to a naive implementation of our approach which can still be accurate, we propose a novel adaptive neighborhood sampling scheme (ANS) that we formally show can be much more sample and query efficient. We then empirically evaluate our approach on real data where our explanations are significantly more sample and query efficient than the competitors, while also being faithful and stable across different widths.

Amit Dhurandhar (IBM); Karthikeyan Natesan Ramamurthy (IBM); Karthikeyan Shanmugam (IBM)

Description:

Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels, but loses accuracy because of the limited amount of available MLR annotations. In this work, we utilize the strong alignment of textual and visual features pretrained with millions of auxiliary image-text pairs and propose \textit{Dual Context Optimization} (DualCoOp) as a unified framework for partial-label MLR and zero-shot MLR. \ours encodes positive and negative contexts with class names as part of the linguistic input (i.e. prompts). Since \ours only introduces a very light learnable overhead upon the pretrained vision-language framework, it can quickly adapt to multi-label recognition tasks that have limited annotations and even unseen classes. Experiments on standard multi-label recognition benchmarks across two challenging low-label settings demonstrate the advantages of our approach over state-of-the-art methods. Our code will be publicly available.Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels, but loses accuracy because of the limited amount of available MLR annotations. In this work, we utilize the strong alignment of textual and visual features pretrained with millions of auxiliary image-text pairs and propose \textit{Dual Context Optimization} (DualCoOp) as a unified framework for partial-label MLR and zero-shot MLR. \ours encodes positive and negative contexts with class names as part of the linguistic input (i.e. prompts). Since \ours only introduces a very light learnable overhead upon the pretrained vision-language framework, it can quickly adapt to multi-label recognition tasks that have limited annotations and even unseen classes. Experiments on standard multi-label recognition benchmarks across two challenging low-label settings demonstrate the advantages of our approach over state-of-the-art methods. Our code will be publicly available.

Ximeng Sun; Ping Hu; Kate Saenko (IBM)

Description:

Reinforcement learning (RL) has gained increasing popularity for resource management in cloud services such as serverless computing. As self-interested users compete for shared resources in a cluster, the multi-tenancy nature of serverless platforms necessitates multi-agent reinforcement learning (MARL) solutions, which often suffer from severe scalability issues. In this paper, we propose a mean-field game (MFG) approach to cloud resource management that is scalable to a large number of users and applications and incorporates function approximation to deal with the large state-action spaces in real-world serverless platforms. Specifically, we present an online natural actor-critic algorithm for learning in MFGs compatible with various forms of function approximation. We theoretically establish its finite-time convergence to the regularized Nash equilibrium under linear function approximation and softmax parameterization. We further implement our algorithm using both linear and neural-network function approximations, and evaluate our solution on an open-source serverless platform, OpenWhisk, with real-world workloads from production traces. Experimental results demonstrate that our approach is scalable to a large number of users and significantly outperforms various baselines in terms of function latency and resource utilization efficiency.

Weichao Mao; Haoran Qiu; Chen Wang (IBM); Hubertus Franke (IBM); Zbigniew T. Kalbarczyk; Ravishankar K. Iyer; Tamer Basar

Description:

Machine learning models often generalize poorly to out-of-distribution (OOD) data as a result of relying on features that are spuriously correlated with the label during training. Recently, the technique of Invariant Risk Minimization (IRM) was proposed to learn predictors that only use invariant features by conserving the feature-conditioned label expectation Ee[y|f(x)] across environments. However, more recent studies have demonstrated that IRM-v1, a practical version of IRM, can fail in various task settings. Here, we identify a fundamental flaw of IRM formulation that causes the failure. We then introduce a complementary notion of invariance, MRI, based on conserving the label-conditioned feature expectation Ee[f(x)|y] across environments, which is free of this flaw. Further, we introduce a simplified, practical version of the MRI formulation called MRI-v1. We note that this constraint is convex which confers it with an advantage over IRM-v1, which imposes non-convex constraints. We prove that in a general linear problem setting, MRI-v1 can guarantee invariant predictors given sufficient environments. We also empirically demonstrate that MRI strongly out-performs IRM and consistently achieves near-optimal OOD generalization in image-based nonlinear problems.

Ben Huh (IBM); Avinash Baidya

Description:

In this paper, we address the challenging problem of 3D concept grounding (i.e., segmenting and learning visual concepts) by looking at RGBD images and reasoning about paired questions and answers. Existing visual reasoning approaches typically utilize supervised methods to extract 2D segmentation masks on which concepts are grounded. In contrast, humans are capable of grounding concepts on the underlying 3D representation of images. However, traditionally inferred 3D representations (e.g., point clouds, voxelgrids and meshes) cannot capture continuous 3D features flexibly, thus making it challenging to ground concepts to 3D regions based on the language description of the object being referred to. To address both issues, we propose to leverage the continuous, differentiable nature of neural fields to segment and learn concepts. Specifically, each 3D coordinate in a scene is represented as a high dimensional descriptor. Concept grounding can then be performed by computing the similarity between the descriptor vector of a 3D coordinate and the vector embedding of a language concept, which enables segmentations and concept learning to be jointly learned on neural fields in a differentiable fashion. As a result, both 3D semantic and instance segmentations can emerge directly from question answering supervision using a set of defined neural operators on top of neural fields (e.g., filtering and counting). Experimental results show that our proposed framework outperforms unsupervised / language-mediated segmentation models on semantic and instance segmentation tasks, as well as outperforms existing models on the challenging 3D aware visual reasoning tasks. Furthermore, our framework can generalize well to unseen shape categories and real scans.

Yining Hong; Yilun Du; Chunru Lin; Josh Tenenbaum; Chuang Gan (IBM)

Description:

Bilevel optimization has been shown to be a powerful framework for formulating multi-task machine learning problems, e.g., reinforcement learning (RL) and meta-learning, where the decision variables are coupled in both levels of the minimization problems. In practice, the learning tasks would be located at different computing resource environments, and thus there is a need for deploying a decentralized training framework to implement multi-agent and multi-task learning. We develop a stochastic linearized augmented Lagrangian method (SLAM) for solving general nonconvex bilevel optimization problems over a graph, where both upper and lower optimization variables are able to achieve a consensus. We also establish that the theoretical convergence rate of the proposed SLAM to the Karush-Kuhn-Tucker (KKT) points of this class of problems is on the same order as the one achieved by the classical distributed stochastic gradient descent for only single-level nonconvex minimization problems. Numerical results tested on multi-agent RL problems showcase the superiority of SLAM compared with the benchmarks.

Songtao Lu (IBM); Siliang Zeng; Xiaodong Cui (IBM); Mark Squillante (IBM); Lior Horesh (IBM); Brian Kingsbury (IBM); Jia Liu; Mingyi Hong

Description:

Despite a surge of recent advances in promoting machine Learning (ML) fairness, the existing mainstream approaches mostly require training or finetuning the entire weights of the neural network to meet the fairness criteria. However, this is often infeasible in practice for those large-scale trained models due to large computational and storage costs, low data efficiency, and model privacy issues. In this paper, we propose a new generic fairness learning paradigm, called FairReprogram, which incorporates the model reprogramming technique. Specifically, FairReprogram considers the neural model fixed, and instead appends to the input a set of perturbations, called the fairness trigger, which is tuned towards the fairness criteria under a min-max formulation. We further introduce an information-theoretic framework that explains why and under what conditions fairness goals can be achieved using the fairness trigger. We show both theoretically and empirically that the fairness trigger can effectively obscure demographic biases in the output prediction of fixed ML models by providing false demographic information that hinders the model from utilizing the correct demographic information to make the prediction. Extensive experiments on both NLP and CV datasets demonstrate that our method can achieve better fairness improvements than retraining-based methods with far less training cost and data dependency under two widely-used fairness criteria.

Guanhua Zhang; Yihua Zhang; Yang Zhang (IBM); Wenqi Fan; Qing Li; Sijia Liu (IBM); Shiyu Chang

Description:

Training machine learning models in a centralized fashion often faces significant challenges due to regulatory and privacy concerns in real-world use cases. These include distributed training data, computational resources to create and maintain a central data repository, and regulatory guidelines (GDPR, HIPAA) that restrict sharing sensitive data. Federated learning (FL) is a new paradigm in machine learning that can mitigate these challenges by training a global model using distributed data, without the need for data sharing. The extensive application of machine learning to analyze and draw insight from real-world, distributed, and sensitive data necessitates familiarization with and adoption of this relevant and timely topic among the scientific community.

Despite the advantages of FL, and its successful application in certain industry-based cases, this field is still in its infancy due to new challenges that are imposed by limited visibility of the training data, potential lack of trust among participants training a single model, potential privacy inferences, and in some cases, limited or unreliable connectivity.

The goal of this workshop is to bring together researchers and practitioners interested in FL. This day-long event will facilitate interaction among students, scholars, and industry professionals from around the world to understand the topic, identify technical challenges, and discuss potential solutions. This will lead to an overall advancement of FL and its impact in the community, while noting that FL has become an increasingly popular topic in the machine learning community in recent years.

Shiqiang Wang (IBM); Nathalie Baracaldo Angel (IBM); Olivia Choudhury; Gauri Joshi; Peter Richtárik; Praneeth Vepakomma; Han Yu

Description:

Molecule optimization is an important problem in chemical discovery and has been approached using many techniques, including generative modeling, reinforcement learning, genetic algorithms, and much more. Recent work has also applied zeroth-order (ZO) optimization, a subset of gradient-free optimization that solves problems similarly to gradient-based methods, for optimizing latent vector representations from an autoencoder. In this paper, we study the effectiveness of various ZO optimization methods for optimizing molecular objectives, which are characterized by variable smoothness, infrequent optima, and other challenges. We provide insights on the robustness of various ZO optimizers in this setting, show the advantages of ZO sign-based gradient descent (ZO-signGD), discuss how ZO optimization can be used practically in realistic discovery tasks, and demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite. Code is available at: https://github.com/IBM/QMO-bench.

Elvin Lo; Pin-Yu Chen (IBM)

Description:

Eye gaze has proven to be a cost-efficient way to collect large-scale physiological data that can reveal the underlying human attentional patterns in real life workflows, and thus has long been explored as a signal to directly measure human-related cognition in various domains. Physiological data (including but not limited to eye gaze) offer new perception capabilities, which could be used in several ML domains, e.g., egocentric perception, embodiedAI, NLP, etc. They can help infer human perception, intentions, beliefs, goals and other cognition properties that are much needed for human-AI interactions and agent coordination. In addition, large collections of eye-tracking data have enabled data-driven modeling of human visual attention mechanisms, both for saliency or scanpath prediction, with twofold advantages: from the neuroscientific perspective to understand biological mechanisms better, from the AI perspective to equip agents with the ability to mimic or predict human behavior and improve interpretability and interactions.

With the emergence of immersive technologies, now more than any time there is a need for experts of various backgrounds (e.g., machine learning, vision, and neuroscience communities) to share expertise and contribute to a deeper understanding of the intricacies of cost-efficient human supervision signals (e.g., eye-gaze) and their utilization towards by bridging human cognition and AI in machine learning research and development. The goal of this workshop is to bring together an active research community to collectively drive progress in defining and addressing core problems in gaze-assisted machine learning.

Ismini Lourentzou; Joy Wu (IBM); Satyananda Kashyap (IBM); Alexandros Karargyris; Leo Anthony Celi; Ban Kawas; Sachin Talathi

Description:

Human-Centered AI (HCAI) is an emerging discipline that aims to create AI systems that amplify and augment human abilities and preserve human control in order to make AI partnerships more productive, enjoyable, and fair. We held a first HCAI@NeurIPS workshop in 2021, with an emphasis in five areas: Interactions of humans and AIs; Methods for human-AI studies; Explainable AI; Ethics; and Fairness.

In 2022, we aim to build on this work by bringing together researchers and practitioners from the NeurIPS and HCI communities and others with convergent interests in HCAI. With an emphasis on diversity and discussion, we will explore research questions that stem from the increasingly wide-spread usage of machine learning algorithms across all areas of society, with a specific focus on understanding both technical and design requirements for HCAI systems, as well as how to evaluate the efficacy and effects of HCAI systems.

Michael Muller (IBM); Plamen Agelov; Hal Daume; Shion Guha; Q. Vera Liao; Nuria Oliver; David Piorkowski (IBM)