/Awesome-Fair-Graph-Learning

Paper List for Fair Graph Learning (FairGL).

MIT LicenseMIT

Awesome Fair Graph Learning

AwesomeContributions Welcome

demo

2024

  • FairGT: A Fairness-aware Graph Transformer, [IJCAI], [Code]
  • Bridging the Fairness Divide: Achieving Group and Individual Fairness in Graph Neural Networks, [arXiv]
  • The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation, [WSDM], [Code]
  • No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation, [AAAI]
  • Chasing Fairness in Graphs: A GNN Architecture Perspective, [AAAI], [Code]
  • Towards Fair Graph Federated Learning via Incentive Mechanisms, [AAAI], [Code]
  • Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach, [ICLR]
  • MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage, [arXiv]
  • Graph Fairness Learning under Distribution Shifts, [WWW], [Code]
  • Disambiguated Node Classification with Graph Neural Networks, [WWW], [Code]
  • Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering, [PAKDD], [Code]
  • GRAPHGINI: Fostering Individual and Group Fairness in Graph Neural Networks, [arXiv]
  • Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization, [AAAI], [Code]
  • Towards Fair Graph Anomaly Detection: Problem, New Datasets, and Evaluation, [arXiv], [Code]
  • Addressing Shortcomings in Fair Graph Learning Datasets: Towards a New Benchmark, [arXiv], [Code]
  • Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks, [arXiv], [Code]
  • Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement, [arXiv], [Code]
  • Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections, [arXiv], [Code]
  • Endowing Pre-trained Graph Models with Provable Fairness, [WWW], [Code]
  • One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes, [KDD], [Code]
  • Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach, [arXiv]
  • Mind the Graph When Balancing Data for Fairness or Robustness, [arXiv]
  • Rethinking Fair Graph Neural Networks from Re-balancing, [KDD], [Code]
  • Fair Augmentation for Graph Collaborative Filtering, [arXiv], [Code]
  • Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks, [arXiv]
  • Promoting Fairness in Link Prediction with Graph Enhancement, [arXiv]

2023

  • Interpreting Unfairness in Graph Neural Networks via Training Node Attribution, [AAAI], [Code]
  • On Generalized Degree Fairness in Graph Neural Networks, [arXiv]
  • Fair Attribute Completion on Graph with Missing Attributes, [arXiv]
  • Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks, [arXiv]
  • Graph Neural Network Surrogates of Fair Graph Filtering, [arXiv]
  • Learning Fair Graph Representations via Automated Data Augmentations, [ICLR]
  • FairGen: Towards Fair Graph Generation, [arXiv]
  • Fair Evaluation of Graph Markov Neural Networks, [arXiv]
  • GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint, [arXiv]
  • Towards Label Position Bias in Graph Neural Networks, [arXiv]
  • BeMap: Balanced Message Passing for Fair Graph Neural Network, [arXiv]
  • Fairness-aware Message Passing for Graph Neural Networks, [arXiv]
  • Improving Fairness of Graph Neural Networks: A Graph Counterfactual Perspective, [arXiv]
  • Fairness-Aware Graph Neural Networks: A Survey, [arXiv]
  • Adversarial Attacks on Fairness of Graph Neural Networks, [arXiv]
  • Fairness-aware Optimal Graph Filter Design, [arXiv]
  • Marginal Nodes Matter: Towards Structure Fairness in Graphs, [arXiv]
  • Deceptive Fairness Attacks on Graphs via Meta Learning, [arXiv]
  • ELEGANT: Certified Defense on the Fairness of Graph Neural Networks, [arXiv], [Code]
  • A Unified Framework for Fair Spectral Clustering With Effective Graph Learning, [arXiv]
  • The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation, [WSDM], [Code]
  • Understanding Community Bias Amplification in Graph Representation Learning, [arXiv]
  • Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction, [ICML, NeurIPS GLFrontiers]
  • FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently, [TKDE]

2022

  • Fairness Amidst Non-IID Graph Data: A Literature Review, [arXiv]
  • Learning Fair Node Representations with Graph Counterfactual Fairness, [WSDM]
  • FMP: Toward Fair Graph Message Passing against Topology Bias, [arXiv]
  • Debiased Graph Neural Networks with Agnostic Label Selection Bias, [TNNLS], [Code]
  • FairRankVis: A Visual Analytics Framework for Exploring Algorithmic Fairness in Graph Mining Models, [IEEE Trans. Vis. Comput. Graph.], [Code]
  • FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing, [arXiv], [Code]
  • RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network, [WWW], [Code]
  • Fair Graph Representation Learning with Imbalanced and Biased Data, [WSDM]
  • FairMod: Fair Link Prediction and Recommendation via Graph Modification, [arXiv]
  • Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness, [AAAI]
  • Fair Node Representation Learning via Adaptive Data Augmentation, [arXiv]
  • Subgroup Fairness in Graph-based Spam Detection, [arXiv]
  • FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings, [ACM TIST]
  • (Survey) A Survey on Fairness for Machine Learning on Graphs, [arXiv]
  • FairNorm: Fair and Fast Graph Neural Network Training, [arXiv]
  • Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage, [arXiv], [Code]
  • On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods, [KDD workshop]
  • GUIDE: Group Equality Informed Individual Fairness in Graph Neural Network, [KDD], [Code]
  • Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks, [ICDM], [Code]
  • Uncovering the Structural Fairness in Graph Contrastive Learning, [NeurIPS], [Code]
  • Item-based Variational Auto-encoder for Fair Music Recommendation, [CIKM]
  • Impact Of Missing Data Imputation On The Fairness And Accuracy Of Graph Node Classifiers, [IEEE Big Data]
  • Graph Learning with Localized Neighborhood Fairness, [arXiv]
  • Graph Self-supervised Learning with Accurate Discrepancy Learning, [NeurIPS], [Code]
  • On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs, [NeurIPS]

2021

  • FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning, [arXiv], [Code]
  • On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections, [ICLR], [Code]
  • Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information, [WSDM], [Code]
  • Subgroup Generalization and Fairness of Graph Neural Networks, [NeurIPS], [Code]
  • Towards a Unified Framework for Fair and Stable Graph Representation Learning, [UAI]
  • Individual Fairness for Graph Neural Networks: A Ranking based Approach, [KDD], [Code]
  • Fair Representation Learning for Heterogeneous Information Networks, [ICWSM], [Code]
  • All of the Fairness for Edge Prediction with Optimal Transport, [AISTATS]
  • CrossWalk: Fairness-enhanced Node Representation Learning, [arXiv]
  • The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer, [ECML-PKDD]
  • Certification and Trade-off of Multiple Fairness Criteria in Graph-based Spam Detection, [CIKM]
  • Post-processing for Individual Fairness, [NeurIPS], [Code]
  • FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings, [ACM Trans. Intell. Syst. Technol]
  • Prior Signal Editing for Graph Filter Posterior Fairness Constraints, [arXiv]
  • Fairness-Aware Node Representation Learning, [arXiv]
  • Fairness-Aware Recommendation in Multi-Sided Platforms, [WSDM]
  • Fairness Violations and Mitigation under Covariate Shift, [ACM FAccT]
  • Fair Graph Auto-Encoder for Unbiased Graph Representations with Wasserstein Distance, [ICDM]
  • A Multi-view Confidence-calibrated Framework for Fair and Stable Graph Representation Learning, [ICDM]
  • Learning Fair Representations for Recommendation: A Graph-based Perspective, [WWW], [Code]

2020

  • Debiasing knowledge graph embeddings, [EMNLP]
  • Fairness-Aware Explainable Recommendation over Knowledge Graphs, [SIGIR], [Code]
  • InFoRM: Individual Fairness on Graph Mining, [KDD], [Code]
  • A Unifying Framework for Fairness-Aware Influence Maximization, [WWW]
  • Applying Fairness Constraints on Graph Node Ranks Under Personalization Bias, [COMPLEX NETWORKS]

2019

  • Fairwalk: Towards Fair Graph Embedding, [IJCAI], [Code]
  • Compositional Fairness Constraints for Graph Embeddings, [ICML], [Code]
  • Exploring Algorithmic Fairness in Robust Graph Covering Problems, [NeurIPS], [Code]