Log In Sign Up

Unified Robust Training for Graph NeuralNetworks against Label Noise

by   Yayong Li, et al.

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.


page 1

page 2

page 3

page 4


Robust Training of Graph Neural Networks via Noise Governance

Graph Neural Networks (GNNs) have become widely-used models for semi-sup...

Informative Pseudo-Labeling for Graph Neural Networks with Few Labels

Graph Neural Networks (GNNs) have achieved state-of-the-art results for ...

Learning Graph Neural Networks with Noisy Labels

We study the robustness to symmetric label noise of GNNs training proced...

Label-Enhanced Graph Neural Network for Semi-supervised Node Classification

Graph Neural Networks (GNNs) have been widely applied in the semi-superv...

On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks

Graph Neural Networks (GNNs) are effective in many applications. Still, ...

Neural Structured Prediction for Inductive Node Classification

This paper studies node classification in the inductive setting, i.e., a...

ASSIST: Towards Label Noise-Robust Dialogue State Tracking

The MultiWOZ 2.0 dataset has greatly boosted the research on dialogue st...