mlsanityData to 7 Oct 2026

Towards Label Position Bias in Graph Neural Networks

arXiv 2305.15822 ↗First posted 25 May 2023cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have emerged as a powerful tool for semi-supervised node classification tasks. However, recent studies have revealed various biases in GNNs stemming from both node features and graph topology. In this work, we uncover a new bias - label position bias, which indicates that the node closer to the labeled nodes tends to perform better. We introduce a new metric, the Label Proximity Score, to quantify this bias, and find that it is closely related to performance disparities. To address the label position bias, we propose a novel optimization framework for learning a label position unbiased graph structure, which can be applied to existing GNNs. Extensive experiments demonstrate that our proposed method not only outperforms backbone methods but also significantly mitigates the issue of label position bias in GNNs.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

39 of 53 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2021Convex optimizationcited by 2,479
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  12. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
27 more
  1. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  2. 2020Simple and Deep Graph Convolutional Networkscited by 857
  3. 2020Towards Deeper Graph Neural Networkscited by 296
  4. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  5. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  6. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  7. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  8. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  9. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  10. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  11. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  12. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  13. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  14. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  15. 2021Elastic Graph Neural Networkscited by 67
  16. 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
  17. 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
  18. 2017Active Learning for Graph Embeddingcited by 53
  19. 2020Multi-hop Attention Graph Neural Networkcited by 53
  20. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
  21. 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
  22. 2022Uncovering the Structural Fairness in Graph Contrastive Learningcited by 29
  23. 2023On Generalized Degree Fairness in Graph Neural Networkscited by 28
  24. 2022Fair Node Representation Learning via Adaptive Data Augmentationcited by 27
  25. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27
  26. 2022Partition-Based Active Learning for Graph Neural Networkscited by 12
  27. 2019Statistical guarantees for local graph clusteringcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approachcited by 17
  2. 2024Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networkscited by 4
  3. 2024Augmenting Textual Generation via Topology Aware Retrievalcited by 1