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}}.

arXiv commentAccepted by IEEE Transactions on Artificial Intelligence

References in corpus (30)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Spectral Networks and Locally Connected Networks on Graphs
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• Variational Graph Auto-Encoders
• Adversarial Feature Learning
• Adversarially Learned Inference
• Pitfalls of Graph Neural Network Evaluation
• Determinantal Processes and Independence
• Towards Deeper Graph Neural Networks
• MolGAN: An implicit generative model for small molecular graphs
• Graph Neural Networks with convolutional ARMA filters
• How Powerful are Graph Neural Networks?
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• NetGAN: Generating Graphs via Random Walks
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• Are Disentangled Representations Helpful for Abstract Visual Reasoning?
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• Adaptive Propagation Graph Convolutional Network
• Factorizable Graph Convolutional Networks
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Multi-Component Graph Convolutional Collaborative Filtering
• Diverse Landmark Sampling from Determinantal Point Processes for Scalable Manifold Learning