Topology-Imbalance Learning for Semi-Supervised Node Classification

TL;DR

This paper identifies a new form of imbalance in graph data called topology imbalance, analyzes its impact on semi-supervised node classification, and proposes a model-agnostic re-weighting method to mitigate it, improving classification performance.

Contribution

The paper introduces the concept of topology imbalance in graphs, provides a unified analysis with quantity imbalance, and proposes the ReNode method to address it effectively.

Findings

ReNode effectively reduces topology imbalance effects.

Topology imbalance significantly affects GNN performance.

The method is generalizable across different GNN architectures.

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.