mlsanityData to 14 Oct 2026

Mitigating Label Noise on Graph via Topological Sample Selection

arXiv 2403.01942 ↗First posted 4 Mar 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world graph data is noisily labeled. Previous explorations in sample selection have been demonstrated as an effective way for robust learning with noisy labels, however, the conventional studies focus on i.i.d data, and when moving to non-iid graph data and GNNs, two notable challenges remain: (1) nodes located near topological class boundaries are very informative for classification but cannot be successfully distinguished by the heuristic sample selection. (2) there is no available measure that considers the graph topological information to promote sample selection in a graph. To address this dilemma, we propose a textitTopological Sample Selection (TSS) method that boosts the informative sample selection process in a graph by utilising topological information. We theoretically prove that our procedure minimizes an upper bound of the expected risk under target clean distribution, and experimentally show the superiority of our method compared with state-of-the-art baselines.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 69 of its 132 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

69 of 132 references.

References · 69

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  8. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  10. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  11. 2017A Closer Look at Memorization in Deep Networkscited by 942
  12. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
38 more
  1. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  2. 2019Multi-scale Attributed Node Embeddingcited by 548
  3. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 413
  4. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  5. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  6. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 260
  7. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  8. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  9. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  10. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  11. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 181
  12. 2020Graph Information Bottleneckcited by 168
  13. 2017Deep Learning is Robust to Massive Label Noisecited by 165
  14. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  15. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  16. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  17. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  18. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  19. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 92
  20. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 88
  21. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  22. 2021FINE Samples for Learning with Noisy Labelscited by 82
  23. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  24. 2020Error-Bounded Correction of Noisy Labelscited by 74
  25. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  26. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  27. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  28. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  29. 2022Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labelscited by 63
  30. 2017Learning with Bounded Instance- and Label-dependent Label Noisecited by 57
  31. 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
  32. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  33. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  34. 2022Towards Open-Set Object Detection and Discoverycited by 44
  35. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  36. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  37. 2022What Makes Graph Neural Networks Miscalibrated?cited by 40
  38. 2019Learning Graph Neural Networks with Noisy Labelscited by 30

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 2.

6 papers.

  1. 2024Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learningcited by 2
  2. 2025Introducing Fractional Classification Loss for Robust Learning with Noisy Labelscited by 2
  3. 2025DeGLIF for Label Noise Robust Node Classification using GNNscited by 1
  4. 2025Training Robust Graph Neural Networks by Modeling Noise Dependenciescited by 0
  5. 2026DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noisecited by 0
  6. 2026UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learningcited by 0