BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction

Abstract

Given the ubiquitous existence of graph-structured data, learning the representations of nodes for the downstream tasks ranging from node classification, link prediction to graph classification is of crucial importance. Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information. However, the available techniques either heavily count on the network topology which is spurious in practice or cannot integrate graph topology and features properly. To bridge the gap, we propose a bicomponent structural and attribute learning framework (BSAL) that is designed to adaptively leverage information from topology and feature spaces. Specifically, BSAL constructs a semantic topology via the node attributes and then gets the embeddings regarding the semantic view, which provides a flexible and easy-to-implement solution to adaptively incorporate the information carried by the node attributes. Then the semantic embedding together with topology embedding is fused together using an attention mechanism for the final prediction. Extensive experiments show the superior performance of our proposal and it significantly outperforms baselines on diverse research benchmarks.

arXiv commentAccepted by SIGIR 2022

References in corpus (19)

• Emergence of scaling in random networks
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Link Prediction in Complex Networks: A Survey
• Predicting Missing Links via Local Information
• Pitfalls of Graph Neural Network Evaluation
• AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
• Hyperbolic Graph Convolutional Neural Networks
• Epidemic spread in weighted scale-free networks
• Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
• GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
• Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
• Personalized PageRank to a Target Node, Revisited
• Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
• ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
• Hyperbolic Graph Neural Networks: A Review of Methods and Applications
• Enhancing Hyperbolic Graph Embeddings via Contrastive Learning
• DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchy