Learning Strong Graph Neural Networks with Weak Information

Abstract

Graph Neural Networks (GNNs) have exhibited impressive performance in many graph learning tasks. Nevertheless, the performance of GNNs can deteriorate when the input graph data suffer from weak information, i.e., incomplete structure, incomplete features, and insufficient labels. Most prior studies, which attempt to learn from the graph data with a specific type of weak information, are far from effective in dealing with the scenario where diverse data deficiencies exist and mutually affect each other. To fill the gap, in this paper, we aim to develop an effective and principled approach to the problem of graph learning with weak information (GLWI). Based on the findings from our empirical analysis, we derive two design focal points for solving the problem of GLWI, i.e., enabling long-range propagation in GNNs and allowing information propagation to those stray nodes isolated from the largest connected component. Accordingly, we propose D${}^2$PT, a dual-channel GNN framework that performs long-range information propagation not only on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities. We further develop a prototype contrastive alignment algorithm that aligns the class-level prototypes learned from two channels, such that the two different information propagation processes can mutually benefit from each other and the finally learned model can well handle the GLWI problem. Extensive experiments on eight real-world benchmark datasets demonstrate the effectiveness and efficiency of our proposed methods in various GLWI scenarios.

arXiv commentAccepted by KDD 2023. 13 pages, 7 figures, 9 tables

References in corpus (29)

• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Pitfalls of Graph Neural Network Evaluation
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Simple and Deep Graph Convolutional Networks
• Scaling Graph Neural Networks with Approximate PageRank
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Missing Data Imputation with Adversarially-trained Graph Convolutional Networks
• Learning Discrete Structures for Graph Neural Networks
• Diffusion Improves Graph Learning
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• Learning on Attribute-Missing Graphs
• Graph Convolutional Networks for Graphs Containing Missing Features
• Graph Attention Multi-Layer Perceptron
• Graph Neural Networks for Graphs with Heterophily: A Survey
• Handling Missing Data with Graph Representation Learning
• Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
• GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection
• Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination
• Model Degradation Hinders Deep Graph Neural Networks
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
• Grale: Designing Networks for Graph Learning
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• Data Augmentation for Deep Graph Learning: A Survey
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Projective Ranking-based GNN Evasion Attacks
• Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity

Cited by in corpus (6)

• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• CVTGAD: Simplified Transformer with Cross-View Attention for Unsupervised Graph-level Anomaly Detection
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• RIDA: A Robust Attack Framework on Incomplete Graphs