AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

Abstract

Graph Convolutional Networks (GCNs) have gained great popularity in tackling various analytics tasks on graph and network data. However, some recent studies raise concerns about whether GCNs can optimally integrate node features and topological structures in a complex graph with rich information. In this paper, we first present an experimental investigation. Surprisingly, our experimental results clearly show that the capability of the state-of-the-art GCNs in fusing node features and topological structures is distant from optimal or even satisfactory. The weakness may severely hinder the capability of GCNs in some classification tasks, since GCNs may not be able to adaptively learn some deep correlation information between topological structures and node features. Can we remedy the weakness and design a new type of GCNs that can retain the advantages of the state-of-the-art GCNs and, at the same time, enhance the capability of fusing topological structures and node features substantially? We tackle the challenge and propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN). The central idea is that we extract the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and use the attention mechanism to learn adaptive importance weights of the embeddings. Our extensive experiments on benchmark data sets clearly show that AM-GCN extracts the most correlated information from both node features and topological structures substantially, and improves the classification accuracy with a clear margin.

11 pages, KDD2020

References in corpus (2)

• LINE: Large-scale Information Network Embedding
• Stochastic blockmodels and community structure in networks

Cited by in corpus (22)

• Mining Latent Structures for Multimedia Recommendation
• Multi-View Graph Convolutional Network for Multimedia Recommendation
• Attention-based graph neural networks: a survey
• Multiplex Heterogeneous Graph Convolutional Network
• DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
• Multi-Behavior Graph Neural Networks for Recommender System
• Single Node Injection Attack against Graph Neural Networks
• SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
• The Expressive Power of Graph Neural Networks: A Survey
• Bi-Level Graph Structure Learning for Next POI Recommendation
• Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily
• DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representations
• Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation
• Multi-view Graph Convolutional Networks with Differentiable Node Selection
• BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
• Near-Real-Time Resource Slicing for QoS Optimization in 5G O-RAN using Deep Reinforcement Learning
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
• Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification
• Robust Distance Covariance
• On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing
• Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks