mlsanityData to 14 Oct 2026

Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark

arXiv 2506.12468 ↗First posted 14 Jun 2025cs.LG cs.AI stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification tasks but struggle with label noise in real-world data. Existing studies on graph learning with label noise commonly rely on class-dependent label noise, overlooking the complexities of instance-dependent noise and falling short of capturing real-world corruption patterns. We introduce BeGIN (Benchmarking for Graphs with Instance-dependent Noise), a new benchmark that provides realistic graph datasets with various noise types and comprehensively evaluates noise-handling strategies across GNN architectures, noisy label detection, and noise-robust learning. To simulate instance-dependent corruptions, BeGIN introduces algorithmic methods and LLM-based simulations. Our experiments reveal the challenges of instance-dependent noise, particularly LLM-based corruption, and underscore the importance of node-specific parameterization to enhance GNN robustness. By comprehensively evaluating noise-handling strategies, BeGIN provides insights into their effectiveness, efficiency, and key performance factors. We expect that BeGIN will serve as a valuable resource for advancing research on label noise in graphs and fostering the development of robust GNN training methods. The code is available at https://github.com/kimsu55/BeGIN.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

38 of 72 references.

References · 38

  1. 2017Graph Attention Networkscited by 8,923
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  8. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  9. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  10. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  11. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
26 more
  1. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  2. 2019Diffusion Improves Graph Learningcited by 414
  3. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  4. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  5. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  6. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
  7. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  8. 2019Human uncertainty makes classification more robustcited by 235
  9. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  10. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  11. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 113
  12. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  13. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 42
  14. 2019Learning Graph Neural Networks with Noisy Labelscited by 30
  15. 2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
  16. 2024The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representationcited by 29
  17. 2022CLNode: Curriculum Learning for Node Classificationcited by 24
  18. 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
  19. 2021Unified Robust Training for Graph NeuralNetworks against Label Noisecited by 21
  20. 2021Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactionscited by 21
  21. 2024Resilience of Large Language Models for Noisy Instructionscited by 20
  22. 2024NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noisecited by 17
  23. 2022Robustness to Label Noise Depends on the Shape of the Noise Distribution in Feature Spacecited by 15
  24. 2023Resurrecting Label Propagation for Graphs with Heterophily and Label Noisecited by 12
  25. 2024Learning Discriminative Dynamics with Label Corruption for Noisy Label Detectioncited by 9
  26. 2024Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Identifying and Correcting Label Noise for Robust GNNs via Influence Contradictioncited by 1
  2. 2026Structured Exploration and Exploitation of Label Functions for Automated Data Annotationcited by 1
  3. 2026Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMscited by 0
  4. 2026Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noisecited by 0