# DeGLIF for Label Noise Robust Node Classification using GNNs

arXiv: https://arxiv.org/abs/2506.00244 · HTML: https://mlsanity.com/paper/2506.00244/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 30 of 30)

- [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)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [A critical look at the evaluation of GNNs under heterophily: Are we really making progress?](https://mlsanity.com/paper/2302.11640/) (2023)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [On the Accuracy of Influence Functions for Measuring Group Effects](https://mlsanity.com/paper/1905.13289/) (2019)
- [Training Data Influence Analysis and Estimation: A Survey](https://mlsanity.com/paper/2212.04612/) (2022)
- [Edge Directionality Improves Learning on Heterophilic Graphs](https://mlsanity.com/paper/2305.10498/) (2023)
- [On Second-Order Group Influence Functions for Black-Box Predictions](https://mlsanity.com/paper/1911.00418/) (2019)
- [NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs](https://mlsanity.com/paper/2106.04714/) (2021)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [Making Risk Minimization Tolerant to Label Noise](https://mlsanity.com/paper/1403.3610/) (2014)
- [Learning Graph Neural Networks with Noisy Labels](https://mlsanity.com/paper/1905.01591/) (2019)
- [Less Is Better: Unweighted Data Subsampling via Influence Function](https://mlsanity.com/paper/1912.01321/) (2019)
- [Robust Training of Graph Neural Networks via Noise Governance](https://mlsanity.com/paper/2211.06614/) (2022)
- [Learning on Graphs under Label Noise](https://mlsanity.com/paper/2306.08194/) (2023)
- [Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions](https://mlsanity.com/paper/2106.07451/) (2021)
- [NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise](https://mlsanity.com/paper/2406.04299/) (2024)
- [Characterizing the Influence of Graph Elements](https://mlsanity.com/paper/2210.07441/) (2022)
- [Deeper Understanding of Black-box Predictions via Generalized Influence Functions](https://mlsanity.com/paper/2312.05586/) (2023)
- [Mitigating Label Noise on Graph via Topological Sample Selection](https://mlsanity.com/paper/2403.01942/) (2024)
- [Cost Sensitive Learning in the Presence of Symmetric Label Noise](https://mlsanity.com/paper/1901.02271/) (2019)

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

- [EDN: A Novel Edge-Dependent Noise Model for Graph Data](https://mlsanity.com/paper/2506.11368/) (2025)

## Abstract (arXiv)

Noisy labelled datasets are generally inexpensive compared to clean labelled datasets, and the same is true for graph data. In this paper, we propose a denoising technique DeGLIF: Denoising Graph Data using Leave-One-Out Influence Function. DeGLIF uses a small set of clean data and the leave-one-out influence function to make label noise robust node-level prediction on graph data. Leave-one-out influence function approximates the change in the model parameters if a training point is removed from the training dataset. Recent advances propose a way to calculate the leave-one-out influence function for Graph Neural Networks (GNNs). We extend that recent work to estimate the change in validation loss, if a training node is removed from the training dataset. We use this estimate and a new theoretically motivated relabelling function to denoise the training dataset. We propose two DeGLIF variants to identify noisy nodes. Both these variants do not require any information about the noise model or the noise level in the dataset; DeGLIF also does not estimate these quantities. For one of these variants, we prove that the noisy points detected can indeed increase risk. We carry out detailed computational experiments on different datasets to show the effectiveness of DeGLIF. It achieves better accuracy than other baseline algorithms