Skip to yearly menu bar Skip to main content


Disentangled Graph Convolutional Networks

Jianxin Ma · Peng Cui · Kun Kuang · Xin Wang · Wenwu Zhu

Pacific Ballroom #175

Keywords: [ Representation Learning ] [ Others ] [ Networks and Relational Learning ] [ Architectures ] [ Algorithms ]

    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.

Live content is unavailable. Log in and register to view live content