Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement

TL;DR

This paper introduces a novel deep generative model that achieves disentangled representation learning for attributed graphs, effectively separating node, edge, and joint factors, with improved architecture and objectives.

Contribution

It proposes a new framework with a variational objective and architecture for disentangling node, edge, and joint factors in attributed graph generation.

Findings

Effective disentanglement of node, edge, and joint factors demonstrated

Improved graph generation quality on synthetic and real datasets

Generalizes image disentanglement frameworks to attributed graphs

Abstract

Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning. However, learning the disentangled representations behind a graph remains largely unexplored, especially for the attributed graph with both node and edge features. Disentanglement learning for graph generation has substantial new challenges including 1) the lack of graph deconvolution operations to jointly decode node and edge attributes; and 2) the difficulty in enforcing the disentanglement among latent factors that respectively influence: i) only nodes, ii) only edges, and iii) joint patterns between them. To address these challenges, we propose a new disentanglement enhancement framework for deep generative models for attributed graphs. In particular, a novel variational objective is proposed to disentangle the above three types of latent factors, with novel architecture for node and edge deconvolutions. Moreover, within each type, individual-factor-wise disentanglement is further enhanced, which is shown to be a generalization of the existing framework for images. Qualitative and quantitative experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed model and its extensions.