Topology-Imbalance Learning for Semi-Supervised Node Classification

Abstract

The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community. Although the imbalance considered by existing studies roots from the unequal quantity of labeled examples in different classes (quantity imbalance), we argue that graph data expose a unique source of imbalance from the asymmetric topological properties of the labeled nodes, i.e., labeled nodes are not equal in terms of their structural role in the graph (topology imbalance). In this work, we first probe the previously unknown topology-imbalance issue, including its characteristics, causes, and threats to semi-supervised node classification learning. We then provide a unified view to jointly analyzing the quantity- and topology- imbalance issues by considering the node influence shift phenomenon with the Label Propagation algorithm. In light of our analysis, we devise an influence conflict detection -- based metric Totoro to measure the degree of graph topology imbalance and propose a model-agnostic method ReNode to address the topology-imbalance issue by re-weighting the influence of labeled nodes adaptively based on their relative positions to class boundaries. Systematic experiments demonstrate the effectiveness and generalizability of our method in relieving topology-imbalance issue and promoting semi-supervised node classification. The further analysis unveils varied sensitivity of different graph neural networks (GNNs) to topology imbalance, which may serve as a new perspective in evaluating GNN architectures.

arXiv commentAccepted By NeurIPS 2021

References in corpus (12)

• SMOTE: Synthetic Minority Over-sampling Technique
• Inductive Representation Learning on Large Graphs
• A systematic study of the class imbalance problem in convolutional neural networks
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Pitfalls of Graph Neural Network Evaluation
• Scaling Graph Neural Networks with Approximate PageRank
• RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Position-aware Graph Neural Networks
• A Survey of Deep Active Learning

Cited by in corpus (4)

• FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks
• Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification
• Using Active Learning Methods to Strategically Select Essays for Automated Scoring
• NodeImport: Imbalanced Node Classification with Node Importance Assessment