Learning Knowledge-diverse Experts for Long-tailed Graph Classification

Zhengyang Mao

doi:10.1145/3705323

Learning Knowledge-diverse Experts for Long-tailed Graph Classification

2025-01-11

0

OA

AI

DOI：10.1145/3705323

Original request for help

Save

Abstract

En 中文

Graph neural networks (GNNs) have shown remarkable success in graph-level classification tasks. However, most of the existing GNN-based studies are based on balanced datasets, while many real-world datasets exhibit long-tailed distributions. In such datasets, the tail classes receive limited attention during training, leading to prediction bias and degraded performance. To address this issue, a range of long-tailed learning strategies have been proposed, such as data re-balancing and transfer learning. However, these approaches encounter several challenges, including insufficient representation capacity for tail classes and their evaluation solely on uniform test data, limiting their capacity to handle unknown class distributions. To tackle these challenges, we introduce a novel framework, namely Knowledge-diverse Experts (KDEX) for long-tailed graph classification. Our KDEX leverages a dynamic memory module to enable the transfer of knowledge from head to tail, which improves the representation ability of the tail. To deal with unknown test distributions, KDEX introduces a knowledge-diverse expert training approach to train experts with different capacities in managing various test distributions. Moreover, we train the hierarchical router in a self-supervised manner to dynamically aggregate each knowledge-diverse expert during testing. Experimental results on multiple benchmarks reveal that our KDEX outperforms current baselines in both standard and test-agnostic long-tailed graph classification.

Keywords:

Graph Neural Network

Long-tailed Learning

Multi-expert Learning

Learning Knowledge-diverse Experts for Long-tailed Graph Classification

Abstract

Journal

Organization