Molecular Inverse-Design Platform for Material Industries
Seiji Takeda, Toshiyuki Hama, et al.
KDD 2020
Inspired by the generation power of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs. The hierarchical architecture consisting of multiple GANs preserves both local and global topological features and automatically partitions the input graph into representative 'stages' for feature learning. The stages facilitate reconstruction and can be used as indicators of the importance of the associated topological structures. The experiments show that our method produces subgraphs retaining a wide range of topological features, even in early reconstruction stages (unlike a single GAN, which cannot easily identify such features, let alone reconstruct the original graph). This paper is the firstline research on combining the use of GANs and graph topological analysis.
Seiji Takeda, Toshiyuki Hama, et al.
KDD 2020
Zhenhan Huang, Tejaswini Pedapati, et al.
ICASSP 2025
Momin Abbas, Muneeza Azmat, et al.
ICLR 2025
Yuya Jeremy Ong, Jay Pankaj Gala, et al.
IEEE CISOSE 2024