# CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection

arXiv: https://arxiv.org/abs/2311.11473 · HTML: https://mlsanity.com/paper/2311.11473/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (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)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [Meta Label Correction for Noisy Label Learning](https://mlsanity.com/paper/1911.03809/) (2019)
- [Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach](https://mlsanity.com/paper/1706.05674/) (2017)
- [Learning with Feature-Dependent Label Noise: A Progressive Approach](https://mlsanity.com/paper/2103.07756/) (2021)
- [Augmentation Strategies for Learning with Noisy Labels](https://mlsanity.com/paper/2103.02130/) (2021)
- [NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs](https://mlsanity.com/paper/2106.04714/) (2021)
- [DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification](https://mlsanity.com/paper/1906.02319/) (2019)
- [Learning Graph Neural Networks with Noisy Labels](https://mlsanity.com/paper/1905.01591/) (2019)
- [Robust Training of Graph Neural Networks via Noise Governance](https://mlsanity.com/paper/2211.06614/) (2022)
- [Loss factorization, weakly supervised learning and label noise robustness](https://mlsanity.com/paper/1602.02450/) (2016)
- [SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise](https://mlsanity.com/paper/2111.11288/) (2021)

## Built on by (most cited first, 1 of 1)

- [Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention](https://mlsanity.com/paper/2312.15033/) (2023)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have emerged as a powerful tool for representation learning on graphs, but they often suffer from overfitting and label noise issues, especially when the data is scarce or imbalanced. Different from the paradigm of previous methods that rely on single-node confidence, in this paper, we introduce a novel Class-wise Selection for Graph Neural Networks, dubbed CSGNN, which employs a neighbor-aggregated latent space to adaptively select reliable nodes across different classes. Specifically, 1) to tackle the class imbalance issue, we introduce a dynamic class-wise selection mechanism, leveraging the clustering technique to identify clean nodes based on the neighbor-aggregated confidences. In this way, our approach can avoid the pitfalls of biased sampling which is common with global threshold techniques. 2) To alleviate the problem of noisy labels, built on the concept of the memorization effect, CSGNN prioritizes learning from clean nodes before noisy ones, thereby iteratively enhancing model performance while mitigating label noise. Through extensive experiments, we demonstrate that CSGNN outperforms state-of-the-art methods in terms of both effectiveness and robustness.