# Resist Label Noise with PGM for Graph Neural Networks

arXiv: https://arxiv.org/abs/2311.02116 · HTML: https://mlsanity.com/paper/2311.02116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods](https://mlsanity.com/paper/2110.14446/) (2021)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [A Fair Comparison of Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/1912.09893/) (2019)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [A Semi-supervised Graph Attentive Network for Financial Fraud Detection](https://mlsanity.com/paper/2003.01171/) (2020)
- [Self-Adaptive Training: beyond Empirical Risk Minimization](https://mlsanity.com/paper/2002.10319/) (2020)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)
- [NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs](https://mlsanity.com/paper/2106.04714/) (2021)
- [Graph-Revised Convolutional Network](https://mlsanity.com/paper/1911.07123/) (2019)
- [Open-set Label Noise Can Improve Robustness Against Inherent Label Noise](https://mlsanity.com/paper/2106.10891/) (2021)
- [Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction](https://mlsanity.com/paper/2006.06648/) (2020)
- [Deep Learning from Noisy Image Labels with Quality Embedding](https://mlsanity.com/paper/1711.00583/) (2017)
- [Learning Graph Neural Networks with Noisy Labels](https://mlsanity.com/paper/1905.01591/) (2019)
- [Weakly Supervised Learning with Side Information for Noisy Labeled Images](https://mlsanity.com/paper/2008.11586/) (2020)
- [Robust Training of Graph Neural Networks via Noise Governance](https://mlsanity.com/paper/2211.06614/) (2022)
- [Unified Robust Training for Graph NeuralNetworks against Label Noise](https://mlsanity.com/paper/2103.03414/) (2021)
- [On Learning Contrastive Representations for Learning with Noisy Labels](https://mlsanity.com/paper/2203.01785/) (2022)

## Abstract (arXiv)

While robust graph neural networks (GNNs) have been widely studied for graph perturbation and attack, those for label noise have received significantly less attention. Most existing methods heavily rely on the label smoothness assumption to correct noisy labels, which adversely affects their performance on heterophilous graphs. Further, they generally perform poorly in high noise-rate scenarios. To address these problems, in this paper, we propose a novel probabilistic graphical model (PGM) based framework LNP. Given a noisy label set and a clean label set, our goal is to maximize the likelihood of labels in the clean set. We first present LNP-v1, which generates clean labels based on graphs only in the Bayesian network. To further leverage the information of clean labels in the noisy label set, we put forward LNP-v2, which incorporates the noisy label set into the Bayesian network to generate clean labels. The generative process can then be used to predict labels for unlabeled nodes. We conduct extensive experiments to show the robustness of LNP on varying noise types and rates, and also on graphs with different heterophilies. In particular, we show that LNP can lead to inspiring performance in high noise-rate situations.