Towards Long-Tailed Recognition for Graph Classification via Collaborative Experts

TL;DR

This paper introduces CoMe, a novel collaborative multi-expert framework for long-tailed graph classification that balances class representation and enhances hard class learning, outperforming existing methods.

Contribution

The paper proposes a new multi-expert learning framework with balanced contrastive learning, hard class mining, and knowledge distillation for long-tailed graph classification.

Findings

CoMe outperforms state-of-the-art baselines on seven benchmark datasets.

Balanced contrastive learning improves representation for tail classes.

Expert collaboration via gated fusion enhances classification accuracy.

Abstract

Graph classification, aiming at learning the graph-level representations for effective class assignments, has received outstanding achievements, which heavily relies on high-quality datasets that have balanced class distribution. In fact, most real-world graph data naturally presents a long-tailed form, where the head classes occupy much more samples than the tail classes, it thus is essential to study the graph-level classification over long-tailed data while still remaining largely unexplored. However, most existing long-tailed learning methods in visions fail to jointly optimize the representation learning and classifier training, as well as neglect the mining of the hard-to-classify classes. Directly applying existing methods to graphs may lead to sub-optimal performance, since the model trained on graphs would be more sensitive to the long-tailed distribution due to the complex topological characteristics. Hence, in this paper, we propose a novel long-tailed graph-level classification framework via Collaborative Multi-expert Learning (CoMe) to tackle the problem. To equilibrate the contributions of head and tail classes, we first develop balanced contrastive learning from the view of representation learning, and then design an individual-expert classifier training based on hard class mining. In addition, we execute gated fusion and disentangled knowledge distillation among the multiple experts to promote the collaboration in a multi-expert framework. Comprehensive experiments are performed on seven widely-used benchmark datasets to demonstrate the superiority of our method CoMe over state-of-the-art baselines.