Learning on Attribute-Missing Graphs

Abstract

Graphs with complete node attributes have been widely explored recently. While in practice, there is a graph where attributes of only partial nodes could be available and those of the others might be entirely missing. This attribute-missing graph is related to numerous real-world applications and there are limited studies investigating the corresponding learning problems. Existing graph learning methods including the popular GNN cannot provide satisfied learning performance since they are not specified for attribute-missing graphs. Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community. In this paper, we make a shared-latent space assumption on graphs and develop a novel distribution matching based GNN called structure-attribute transformer (SAT) for attribute-missing graphs. SAT leverages structures and attributes in a decoupled scheme and achieves the joint distribution modeling of structures and attributes by distribution matching techniques. It could not only perform the link prediction task but also the newly introduced node attribute completion task. Furthermore, practical measures are introduced to quantify the performance of node attribute completion. Extensive experiments on seven real-world datasets indicate SAT shows better performance than other methods on both link prediction and node attribute completion tasks. Codes and data are available online: https://github.com/xuChenSJTU/SAT-master-online

This paper is to appear in IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (TPAMI), 2020

References in corpus (22)

• Efficient Estimation of Word Representations in Vector Space
• Auto-Encoding Variational Bayes
• DeepWalk: Online Learning of Social Representations
• Inductive Representation Learning on Large Graphs
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Deep Visual Domain Adaptation: A Survey
• KGAT: Knowledge Graph Attention Network for Recommendation
• Variational Inference with Normalizing Flows
• Simplifying Graph Convolutional Networks
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• Graph Convolutional Matrix Completion
• Variational Graph Auto-Encoders
• Pitfalls of Graph Neural Network Evaluation
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Self-Attention Graph Pooling
• InfoVAE: Information Maximizing Variational Autoencoders
• Adversarial Autoencoders
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Distribution Matching in Variational Inference
• Semi-Implicit Variational Inference
• Degeneration in VAE: in the Light of Fisher Information Loss

Cited by in corpus (6)

• Learning Strong Graph Neural Networks with Weak Information
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Time-Synchronized State Estimation Using Graph Neural Networks in Presence of Topology Changes
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Clustering-Oriented Generative Attribute Graph Imputation