Timezone: »

 
Poster
Molecule Generation by Principal Subgraph Mining and Assembling
Xiangzhe Kong · Wenbing Huang · Zhixing Tan · Yang Liu

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #213
in Poster Session 5 »

Molecule generation is central to a variety of applications. Current attention has been paid to approaching the generation task as subgraph prediction and assembling. Nevertheless, these methods usually rely on hand-crafted or external subgraph construction, and the subgraph assembling depends solely on local arrangement. In this paper, we define a novel notion, principal subgraph that is closely related to the informative pattern within molecules. Interestingly, our proposed merge-and-update subgraph extraction method can automatically discover frequent principal subgraphs from the dataset, while previous methods are incapable of. Moreover, we develop a two-step subgraph assembling strategy, which first predicts a set of subgraphs in a sequence-wise manner and then assembles all generated subgraphs globally as the final output molecule. Built upon graph variational auto-encoder, our model is demonstrated to be effective in terms of several evaluation metrics and efficiency, compared with state-of-the-art methods on distribution learning and (constrained) property optimization tasks.

Keywords: molecule generation · principal subgraph · global assembling
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Xiangzhe Kong (Tsinghua University)
Wenbing Huang (Tsinghua University)
Zhixing Tan (Tsinghua University, Tsinghua University)
Yang Liu (Tsinghua University)

More from the Same Authors