Adversarial Graph Disentanglement

Abstract

A real-world graph has a complex topological structure, which is often formed by the interaction of different latent factors. However, most existing methods lack consideration of the intrinsic differences in relations between nodes caused by factor entanglement. In this paper, we propose an \underline{\textbf{A}}dversarial \underline{\textbf{D}}isentangled \underline{\textbf{G}}raph \underline{\textbf{C}}onvolutional \underline{\textbf{N}}etwork (ADGCN) for disentangled graph representation learning. To begin with, we point out two aspects of graph disentanglement that need to be considered, i.e., micro-disentanglement and macro-disentanglement. For them, a component-specific aggregation approach is proposed to achieve micro-disentanglement by inferring latent components that cause the links between nodes. On the basis of micro-disentanglement, we further propose a macro-disentanglement adversarial regularizer to improve the separability among component distributions, thus restricting the interdependence among components. Additionally, to reveal the topological graph structure, a diversity-preserving node sampling approach is proposed, by which the graph structure can be progressively refined in a way of local structure awareness. The experimental results on various real-world graph data verify that our ADGCN obtains more favorable performance over currently available alternatives. The source codes of ADGCN are available at \textit{\url{https://github.com/SsGood/ADGCN}}.

Accepted by IEEE Transactions on Artificial Intelligence

References in corpus (9)

• Conditional Generative Adversarial Nets
• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• Towards Deeper Graph Neural Networks
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Factorizable Graph Convolutional Networks
• Multi-Component Graph Convolutional Collaborative Filtering
• Diverse Landmark Sampling from Determinantal Point Processes for Scalable Manifold Learning