Unified Robust Training for Graph NeuralNetworks against Label Noise

TL;DR

This paper introduces UnionNET, a unified semi-supervised framework for robustly training graph neural networks in the presence of label noise, without requiring clean labels or noise transition matrices.

Contribution

UnionNET is a novel framework that combines label aggregation, sample reweighting, and label correction for robust GNN training under label noise without extra supervision.

Findings

Effective against various label noise types and levels

Significant improvements over state-of-the-art methods

End-to-end training without noise transition matrices

Abstract

Graph neural networks (GNNs) have achieved state-of-the-art performance for node classification on graphs. The vast majority of existing works assume that genuine node labels are always provided for training. However, there has been very little research effort on how to improve the robustness of GNNs in the presence of label noise. Learning with label noise has been primarily studied in the context of image classification, but these techniques cannot be directly applied to graph-structured data, due to two major challenges -- label sparsity and label dependency -- faced by learning on graphs. In this paper, we propose a new framework, UnionNET, for learning with noisy labels on graphs under a semi-supervised setting. Our approach provides a unified solution for robustly training GNNs and performing label correction simultaneously. The key idea is to perform label aggregation to estimate node-level class probability distributions, which are used to guide sample reweighting and label correction. Compared with existing works, UnionNET has two appealing advantages. First, it requires no extra clean supervision, or explicit estimation of the noise transition matrix. Second, a unified learning framework is proposed to robustly train GNNs in an end-to-end manner. Experimental results show that our proposed approach: (1) is effective in improving model robustness against different types and levels of label noise; (2) yields significant improvements over state-of-the-art baselines.