Timezone: »

 
Oral
Disentangled Graph Convolutional Networks
Jianxin Ma · Peng Cui · Kun Kuang · Xin Wang · Wenwu Zhu

Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Room 102
in Networks and Relational Learning » 
    The formation of a real-world graph typically arises from the highly complex interaction of many latent factors.
    The existing deep learning methods for graph-structured data neglect the entanglement of the latent factors, rendering the learned representations non-robust and hardly explainable.
    However, learning representations that disentangle the latent factors poses great challenges and remains largely unexplored in the literature of graph neural networks.
    In this paper, we introduce the disentangled graph convolutional network (DisenGCN) to learn disentangled node representations.
    In particular, we propose a novel neighborhood routing mechanism, which is capable of dynamically identifying the latent factor that may have caused the edge between a node and one of its neighbors,  and accordingly assigning the neighbor to a channel that extracts and convolutes features specific to that factor.
    We theoretically prove the convergence properties of the routing mechanism.
    Empirical results show that our proposed model can achieve significant performance gains, especially when the data demonstrate the existence of many entangled factors.
[ Slides]  [ Video] 

Author Information

Jianxin Ma (Tsinghua University)
Peng Cui (Tsinghua University)
Peng Cui

Peng Cui is an Associate Professor in Tsinghua University. He got his PhD degree from Tsinghua University in 2010. His research interests include causal inference and stable learning, network representation learning, and human behavioral modeling. He has published more than 100 papers in prestigious conferences and journals in data mining and multimedia. His recent research won the IEEE Multimedia Best Department Paper Award, SIGKDD 2016 Best Paper Finalist, ICDM 2015 Best Student Paper Award, SIGKDD 2014 Best Paper Finalist, IEEE ICME 2014 Best Paper Award, ACM MM12 Grand Challenge Multimodal Award, and MMM13 Best Paper Award. He is the Associate Editors of IEEE TKDE, IEEE TBD, ACM TIST, and ACM TOMM etc. He has served as program co-chair and area chair of several major machine learning and artificial intelligence conferences, such as IJCAI, AAAI, ACM CIKM, ACM Multimedia etc.

Kun Kuang (Tsinghua University)
Xin Wang (Tsinghua University)
Wenwu Zhu (Tsinghua University)

Wenwu Zhu is currently a Professor of Computer Science Department of Tsinghua University and Vice Dean of National Research Center on Information Science and Technology. Prior to his current post, he was a Senior Researcher and Research Manager at Microsoft Research Asia. He was the Chief Scientist and Director at Intel Research China from 2004 to 2008. He worked at Bell Labs New Jersey as a Member of Technical Staff during 1996-1999. He has been serving as the chair of the steering committee for IEEE T-MM since January 1, 2020. He served as the Editor-in-Chief for the IEEE Transactions on Multimedia (T-MM) from 2017 to 2019. And Vice EiC for IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) from 2020-2021 He served as co-Chair for ACM MM 2018 and co-Chair for ACM CIKM 2019. His current research interests are in the areas of multimodal big data and intelligence, and multimedia networking. He received 10 Best Paper Awards. He is a member of Academia Europaea, an IEEE Fellow, AAAS Fellow, and SPIE Fellow.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors