Show simple item record

dc.contributor.authorSong, Y
dc.contributor.authorZheng, S
dc.contributor.authorNiu, Z
dc.contributor.authorFu, ZH
dc.contributor.authorLu, Y
dc.contributor.authorYang, Y
dc.date.accessioned2021-01-29T03:25:20Z
dc.date.available2021-01-29T03:25:20Z
dc.date.issued2020
dc.identifier.isbn9780999241165
dc.identifier.issn1045-0823
dc.identifier.doi10.24963/ijcai.2020/392
dc.identifier.urihttp://hdl.handle.net/10072/401561
dc.description.abstractConstructing proper representations of molecules lies at the core of numerous tasks such as molecular property prediction and drug design. Graph neural networks, especially message passing neural network (MPNN) and its variants, have recently made remarkable achievements in molecular graph modeling. Albeit powerful, the one-sided focuses on atom (node) or bond (edge) information of existing MPNN methods lead to the insufficient representations of the attributed molecular graphs. Herein, we propose a Communicative Message Passing Neural Network (CMPNN) to improve the molecular embedding by strengthening the message interactions between nodes and edges through a communicative kernel. In addition, the message generation process is enriched by introducing a new message booster module. Extensive experiments demonstrated that the proposed model obtained superior performances against state-of-the-art baselines on six chemical property datasets. Further visualization also showed better representation capacity of our model.
dc.description.peerreviewedYes
dc.publisherInternational Joint Conferences on Artificial Intelligence Organization
dc.relation.ispartofconferencename29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI2020)
dc.relation.ispartofconferencetitleProceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
dc.relation.ispartofdatefrom2021-01-07
dc.relation.ispartofdateto2021-01-15
dc.relation.ispartoflocationYokohama, Japan
dc.relation.ispartofpagefrom2831
dc.relation.ispartofpageto2838
dc.subject.fieldofresearchArtificial intelligence
dc.subject.fieldofresearchcode4602
dc.titleCommunicative representation learning on attributed molecular graphs
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationSong, Y; Zheng, S; Niu, Z; Fu, ZH; Lu, Y; Yang, Y, Communicative representation learning on attributed molecular graphs, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020, 2021-January, pp. 2831-2838
dc.date.updated2021-01-29T03:22:46Z
dc.description.versionVersion of Record (VoR)
gro.rights.copyright© 2021 International Joint Conference on Artificial Intelligence. The attached file is reproduced here in accordance with the copyright policy of the publisher. Please refer to the Conference's website for access to the definitive, published version.
gro.hasfulltextFull Text
gro.griffith.authorYang, Yuedong


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record