Learning Knowledge-diverse Experts for Long-tailed Graph Classification
Open Access
- 11 January 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (2) , 1-24
Abstract
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
Funding Information
- National Key Research and Development Program of China (2023YFC3341203)
- National Natural Science Foundation of China (62306014, 62276002)
- Postdoctoral Fellowship Program (Grade A) of CPSF (BX20240239)
This publication has 50 references indexed in Scilit:
- COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic ForecastingInformation Fusion, 2024
- A graph neural network-based node classification model on class-imbalanced graph dataKnowledge-Based Systems, 2022
- Addressing bias in prediction models by improving subpopulation calibrationJournal of the American Medical Informatics Association, 2021
- Large-Scale Long-Tailed Recognition in an Open World2019
- Class-Balanced Loss Based on Effective Number of Samples2019
- Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning2018
- The MIMIC Code Repository: enabling reproducibility in critical care researchJournal of the American Medical Informatics Association, 2017
- Variational Bayesian mixture of experts models and sensitivity analysis for nonlinear dynamical systemsMechanical Systems and Signal Processing, 2016
- Propagation kernels: efficient graph kernels from propagated informationMachine Learning, 2015
- IAM Graph Database Repository for Graph Based Pattern Recognition and Machine Learning2008