mlsanityData to 7 Oct 2026

RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network

arXiv 2202.13547 ↗First posted 28 Feb 2022cs.LG cs.SIcited by 27

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Network (GCN) plays pivotal roles in many real-world applications. Despite the successes of GCN deployment, GCN often exhibits performance disparity with respect to node degrees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related performance disparity in GCN from the perspective of the Rawlsian difference principle, which is originated from the theory of distributive justice. Mathematically, we aim to balance the utility between low-degree nodes and high-degree nodes while minimizing the task-specific loss. Specifically, we reveal the root cause of this degree-related unfairness by analyzing the gradients of weight matrices in GCN. Guided by the gradients of weight matrices, we further propose a pre-processing method RawlsGCN-Graph and an in-processing method RawlsGCN-Grad that achieves fair predictive accuracy in low-degree nodes without modification on the GCN architecture or introduction of additional parameters. Extensive experiments on real-world graphs demonstrate the effectiveness of our proposed RawlsGCN methods in significantly reducing degree-related bias while retaining comparable overall performance.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 28 Feb 2022.

Builds on

20 of 32 references.

References · 20

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  6. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  7. 2019Neural Graph Collaborative Filteringcited by 660
  8. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  9. 2015Diffusion-Convolutional Neural Networkscited by 268
  10. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  11. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  12. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
8 more
  1. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  2. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  3. 2019Guarantees for Spectral Clustering with Fairness Constraintscited by 72
  4. 2019DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classificationcited by 59
  5. 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
  6. 2021Network of Tensor Time Seriescited by 32
  7. 2020Exploring Algorithmic Fairness in Robust Graph Covering Problemscited by 19
  8. 2018Conditional Network Embeddingscited by 15

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 8; 2024: 4; 2025: 8.

27 papers.

Sort:

By area:

  1. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  2. 2022Fairness in Graph Mining: A Surveycited by 76
  3. 2022Uncovering the Structural Fairness in Graph Contrastive Learningcited by 29
  4. 2023Class-Imbalanced Graph Learning without Class Rebalancingcited by 29
  5. 2023On Generalized Degree Fairness in Graph Neural Networkscited by 28
  6. 2023Fairness-Aware Graph Neural Networks: A Surveycited by 22
  7. 2022On Structural Explanation of Bias in Graph Neural Networkscited by 15
  8. 2022JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networkscited by 14
  9. 2024FUGNN: Harmonizing Fairness and Utility in Graph Neural Networkscited by 11
  10. 2023Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Predictioncited by 8
  11. 2024FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficientlycited by 8
  12. 2023Deceptive Fairness Attacks on Graphs via Meta Learningcited by 6
15 more
  1. 2024Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networkscited by 4
  2. 2023Towards Label Position Bias in Graph Neural Networkscited by 3
  3. 2024GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networkscited by 3
  4. 2025Fairness in Augmented Graph Learning: A Surveycited by 2
  5. 2023CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphscited by 1
  6. 2022TuneUp: A Simple Improved Training Strategy for Graph Neural Networkscited by 0
  7. 2022Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbationcited by 0
  8. 2023Understanding Community Bias Amplification in Graph Representation Learningcited by 0
  9. 2025FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Trainingcited by 0
  10. 2025Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attentioncited by 0
  11. 2025SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encodingcited by 0
  12. 2025Adaptive Node Feature Selection For Graph Neural Networkscited by 0
  13. 2025When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approachcited by 0
  14. 2025FnRGNN: Distribution-aware Fairness in Graph Neural Networkcited by 0
  15. 2025Mitigating Bias in Graph Hyperdimensional Computingcited by 0