Disambiguated Node Classification with Graph Neural Networks

Abstract

Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data across various domains. Despite their great successful, one critical challenge is often overlooked by existing works, i.e., the learning of message propagation that can generalize effectively to underrepresented graph regions. These minority regions often exhibit irregular homophily/heterophily patterns and diverse neighborhood class distributions, resulting in ambiguity. In this work, we investigate the ambiguity problem within GNNs, its impact on representation learning, and the development of richer supervision signals to fight against this problem. We conduct a fine-grained evaluation of GNN, analyzing the existence of ambiguity in different graph regions and its relation with node positions. To disambiguate node embeddings, we propose a novel method, {\method}, which exploits additional optimization guidance to enhance representation learning, particularly for nodes in ambiguous regions. {\method} identifies ambiguous nodes based on temporal inconsistency of predictions and introduces a disambiguation regularization by employing contrastive learning in a topology-aware manner. {\method} promotes discriminativity of node representations and can alleviating semantic mixing caused by message propagation, effectively addressing the ambiguity problem. Empirical results validate the efficiency of {\method} and highlight its potential to improve GNN performance in underrepresented graph regions.

arXiv commentAccepted by WebConf (WWW) 2024

References in corpus (11)

• A Comprehensive Survey on Graph Neural Networks
• Contrastive Representation Learning: A Framework and Review
• Graph Self-Supervised Learning: A Survey
• GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
• A Comprehensive Survey on Deep Graph Representation Learning
• Gated Graph Recurrent Neural Networks
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• Exploring Edge Disentanglement for Node Classification
• Towards Faithful and Consistent Explanations for Graph Neural Networks
• Semi-Supervised Graph-to-Graph Translation

Cited by in corpus (2)

• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• Curriculum Guided Personalized Subgraph Federated Learning