Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Survey on Fairness for Machine Learning on Graphs (2205.05396v2)

Published 11 May 2022 in cs.LG

Abstract: Nowadays, the analysis of complex phenomena modeled by graphs plays a crucial role in many real-world application domains where decisions can have a strong societal impact. However, numerous studies and papers have recently revealed that machine learning models could lead to potential disparate treatment between individuals and unfair outcomes. In that context, algorithmic contributions for graph mining are not spared by the problem of fairness and present some specific challenges related to the intrinsic nature of graphs: (1) graph data is non-IID, and this assumption may invalidate many existing studies in fair machine learning, (2) suited metric definitions to assess the different types of fairness with relational data and (3) algorithmic challenge on the difficulty of finding a good trade-off between model accuracy and fairness. This survey is the first one dedicated to fairness for relational data. It aims to present a comprehensive review of state-of-the-art techniques in fairness on graph mining and identify the open challenges and future trends. In particular, we start by presenting several sensible application domains and the associated graph mining tasks with a focus on edge prediction and node classification in the sequel. We also recall the different metrics proposed to evaluate potential bias at different levels of the graph mining process; then we provide a comprehensive overview of recent contributions in the domain of fair machine learning for graphs, that we classify into pre-processing, in-processing and post-processing models. We also propose to describe existing graph data, synthetic and real-world benchmarks. Finally, we present in detail five potential promising directions to advance research in studying algorithmic fairness on graphs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (99)
  1. Lada A Adamic and Natalie Glance. 2005. The political blogosphere and the 2004 US election: divided they blog. In Proceedings of the 3rd international workshop on Link discovery. ACM, Chicago Illinois, 36–43.
  2. One-network adversarial fairness. In AAAI Conference on Artificial Intelligence, Vol. 33. AAAI Press, Hawaii, USA, 2412–2420.
  3. Towards a unified framework for fair and stable graph representation learning. In Uncertainty in Artificial Intelligence. PMLR, AUAI Press, Online, 2114–2124.
  4. Charu C. Aggarwal and Haixun Wang (Eds.). 2010. Managing and Mining Graph Data. Springer. https://doi.org/10.1007/978-1-4419-6045-0
  5. On the Fairness of Time-Critical Influence Maximization in Social Networks. IEEE Trans. Knowl. Data Eng. 35, 3 (2023), 2875–2886.
  6. Fairness and Machine Learning. fairmlbook.org. http://www.fairmlbook.org.
  7. Solon Barocas and Andrew D Selbst. 2016. Big data’s disparate impact. Calif. L. Rev. 104 (2016), 671.
  8. Marianne Bertrand and Sendhil Mullainathan. 2003. Are Emily and Greg More Employable than Lakisha and Jamal? A Field Experiment on Labor Market Discrimination. Working Paper 9873. National Bureau of Economic Research. https://doi.org/10.3386/w9873
  9. Putting fairness principles into practice: Challenges, metrics, and improvements. In AAAI/ACM Conference on AI, Ethics, and Society. 453–459.
  10. Node classification in social networks. In Social network data analytics. Springer, 115–148.
  11. Avishek Bose and William Hamilton. 2019. Compositional fairness constraints for graph embeddings. In ICML. PMLR, 715–724.
  12. Maarten Buyl and Tijl De Bie. 2020. DeBayes: a Bayesian method for debiasing network embeddings. In Proceedings ICML. 2537–2546.
  13. Maarten Buyl and Tijl De Bie. 2021. The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer. In Proceedings ECML-PKDD.
  14. Simon Caton and Christian Haas. 2020. Fairness in Machine Learning: A Survey. arXiv:2010.04053 (2020).
  15. Classification with fairness constraints: A meta-algorithm with provable guarantees. In Conference on fairness, accountability, and transparency. 319–328.
  16. Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals. Journal of Machine Learning Research 20, 172 (2019), 1–59.
  17. Flexibly fair representation learning by disentanglement. arXiv preprint arXiv:1906.02589 (2019).
  18. FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification. In Equity and Access in Algorithms, Mechanisms, and Optimization, EAAMO. ACM, 3:1–3:14.
  19. Enyan Dai and Suhang Wang. 2021. Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information. In International Conference on Web Search and Data Mining. Association for Computing Machinery, 680–688.
  20. Individual Fairness for Graph Neural Networks: A Ranking Based Approach. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 300–310.
  21. EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks. In WWW : The ACM Web Conference, Frédérique Laforest, Raphaël Troncy, Elena Simperl, Deepak Agarwal, Aristides Gionis, Ivan Herman, and Lionel Médini (Eds.). ACM, 1259–1269.
  22. Fairness in Graph Mining: A Survey. IEEE Transactions on Knowledge & Data Engineering (2023), 1–22.
  23. On Structural Explanation of Bias in Graph Neural Networks. In KDD: The ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aidong Zhang and Huzefa Rangwala (Eds.). ACM, 316–326.
  24. Fairness in Deep Learning: A Computational Perspective. IEEE Intell. Syst. 36, 4 (2021), 25–34.
  25. Fairness through awareness. In ITCS. 214–226.
  26. Decoupled classifiers for group-fair and efficient machine learning. In Conference on Fairness, Accountability and Transparency. 119–133.
  27. H. Edwards and A. Storkey. 2016. Censoring representations with an adversary.. In International Conference in Learning Representation ICLR. 1–14.
  28. Santo Fortunato. 2010. Community detection in graphs. Physics reports 486, 3-5 (2010), 75–174.
  29. Bruce Glymour and Jonathan Herington. 2019. Measuring the biases that matter: The ethical and casual foundations for measures of fairness in algorithms. In Conference on fairness, accountability, and transparency. 269–278.
  30. A Kernel Method for the Two-Sample-Problem. In Advances in Neural Information Processing Systems.
  31. Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 855–864.
  32. Inductive Representation Learning on Large Graphs. In Proceedings of NeurIPS, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30.
  33. Equality of Opportunity in Supervised Learning. In Proceedings NeurIPS. 3323–3331.
  34. Equality of opportunity in supervised learning. Advances in neural information processing systems 29 (2016), 3315–3323.
  35. On the Information Unfairness of Social Networks. 613–521.
  36. Conditional network embeddings. In International Conference on Learning Representations.
  37. InFoRM: Individual Fairness on Graph Mining. In SIGKDD International Conference on Knowledge Discovery & Data Mining. 379–389.
  38. InFoRM: Individual Fairness on Graph Mining. In Proceedings of SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’20). Association for Computing Machinery, New York, NY, USA, 379–389.
  39. Jian Kang and Hanghang Tong. 2021. Fair Graph Mining. Association for Computing Machinery, 4849–4852.
  40. Jian Kang and Hanghang Tong Wan. [n.d.]. Algorithmic Fairness on Graphs: Methods and Trends. KDD 2022 ([n. d.]).
  41. Maximizing the Spread of Influence through a Social Network. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 137-146 (2003). https://doi.org/10.1145/956750.956769
  42. Personalized Job Recommendation System at LinkedIn: Practical Challenges and Lessons Learned. In Proceedings of RecSys (Como, Italy). Association for Computing Machinery, 346–347. https://doi.org/10.1145/3109859.3109921
  43. CrossWalk: Fairness-Enhanced Node Representation Learning. In AAAI Conference on Artificial Intelligence. AAAI Press, 11963–11970.
  44. Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks. In Proceedings of IJCAI (IJCAI’20). Article 594, 7 pages.
  45. Fairness through computationally-bounded awareness. In Neural Information Processing Systems. 4847–4857.
  46. Diederik P Kingma and Max Welling. 2014. Auto-encoding variational bayes. ICLR 2014 (2014).
  47. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings ICLR.
  48. Guarantees for Spectral Clustering with Fairness Constraints. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 3458–3467. http://proceedings.mlr.press/v97/kleindessner19b.html
  49. Counterfactual Fairness. In Proceedings NeurIPS. 4069–4079.
  50. All of the Fairness for Edge Prediction with Optimal Transport. In International Conference on Artificial Intelligence and Statistics. 1774–1782.
  51. iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making. In International Conference on Data Engineering, ICDE. IEEE, 1334–1345. https://doi.org/10.1109/ICDE.2019.00121
  52. Benchmark graphs for testing community detection algorithms. Physical Review E 78, 4 (2008). https://doi.org/10.1103/physreve.78.046110
  53. DANCer: dynamic attributed networks with community structure generation. Knowl. Inf. Syst. 53, 1 (2017), 109–151.
  54. A survey on datasets for fairness-aware machine learning. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 12, 3 (2022), e1452.
  55. On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections. In International Conference on Learning Representations, ICLR.
  56. The Variational Fair Autoencoder. In ICLR.
  57. Subgroup generalization and fairness of graph neural networks. Advances in Neural Information Processing Systems 34 (2021).
  58. Learning adversarially fair and transferable representations. In ICML. 3384–3393.
  59. Gianclaudio Malgieri. 2020. The Concept of Fairness in the GDPR: A Linguistic and Contextual Interpretation. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. 154–166.
  60. Bursting the Filter Bubble: Fairness-Aware Network Link Prediction. AAAI Conference on Artificial Intelligence 34, 01 (2020), 841–848.
  61. Julian J McAuley and Jure Leskovec. 2012. Learning to discover social circles in ego networks.. In NIPS, Vol. 2012. 548–56.
  62. Birds of a Feather: Homophily in Social Networks. Annual Review of Sociology 27, 1 (2001), 415–444.
  63. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 6, Article 115 (jul 2021), 35 pages. https://doi.org/10.1145/3457607
  64. Algorithmic Fairness: Choices, Assumptions, and Definitions. Annual Review of Statistics and Its Application 8, 1 (2021), 141–163.
  65. Razieh Nabi and Ilya Shpitser. 2018. Fair inference on outcomes. In AAAI Conference on Artificial Intelligence, Vol. 32.
  66. M. E. J. Newman. 2003. Mixing patterns in networks. Physical Review E 67, 2 (Feb 2003). https://doi.org/10.1103/physreve.67.026126
  67. Taking advantage of multitask learning for fair classification. In AAAI/ACM Conference on AI, Ethics, and Society. 227–237.
  68. Learning Deep Fair Graph Neural Networks. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 31–36.
  69. Philip Oreopoulos. 2011. Why Do Skilled Immigrants Struggle in the Labor Market? A Field Experiment with Thirteen Thousand Resumes. American Economic Journal: Economic Policy 3, 4 (November 2011), 148–71. https://doi.org/10.1257/pol.3.4.148
  70. The PageRank Citation Ranking: Bringing Order to the Web. Technical Report. Stanford InfoLab.
  71. John Palowitch and Bryan Perozzi. 2020. MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit. In IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.
  72. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 701–710.
  73. Fairness in Rankings and Recommendations: An Overview. The VLDB Journal 31, 3 (2021), 431–458.
  74. Fairwalk: Towards Fair Graph Embedding.. In IJCAI. 3289–3295.
  75. Fair Influence Maximization: a Welfare Optimization Approach. In AAAI Conference on Artificial Intelligence. AAAI Press, 11630–11638.
  76. Exploring Algorithmic Fairness in Robust Graph Covering Problems. In Advances in Neural Information Processing Systems. 15750–15761.
  77. Stochastic backpropagation and approximate inference in deep generative models. In International conference on machine learning. PMLR, 1278–1286.
  78. On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs With Missing Node Features. In Learning on Graphs Conference, LoG 2022, 9-12 December 2022, Virtual Event, Vol. 198. 11.
  79. Multi-Scale attributed node embedding. Journal of Complex Networks 9, 2 (2021), cnab014.
  80. Benedek Rozemberczki and Rik Sarkar. 2020. Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models. In International Conference on Information and Knowledge Management (CIKM ’20). 1325–1334.
  81. HM-EIICT: Fairness-aware link prediction in complex networks using community information. J. Comb. Optim. 44, 4 (2022), 2853–2870.
  82. FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning. IEEE Transactions on Artificial Intelligence (2021).
  83. A Comprehensive Survey on Community Detection With Deep Learning. IEEE Transactions on Neural Networks and Learning Systems (2022), 1–21. https://doi.org/10.1109/TNNLS.2021.3137396
  84. Lubos Takac and Michal Zabovsky. 2012. Data analysis in public social networks. In International scientific conference and international workshop present day trends of innovations, Vol. 1.
  85. LINE: Large-Scale Information Network Embedding. In Proceedings of WWW. 1067–1077. https://doi.org/10.1145/2736277.2741093
  86. What-Is and How-To for Fairness in Machine Learning: A Survey, Reflection, and Perspective. ACM Comput. Surv. (2023).
  87. Group-Fairness in Influence Maximization. In IJCAI, Sarit Kraus (Ed.). 5997–6005.
  88. Fairness without harm: Decoupled classifiers with preference guarantees. In International Conference on Machine Learning. 6373–6382.
  89. Fairness in Networks. KDD 2021 ([n. d.]).
  90. In-Processing Modeling Techniques for Machine Learning Fairness: A Survey. ACM Transactions on Knowledge Discovery from Data ([n. d.]). https://doi.org/10.1145/3551390
  91. Unbiased Graph Embedding with Biased Graph Observations. In Proceedings of WWW. Association for Computing Machinery, 1423–1433. https://doi.org/10.1145/3485447.3512189
  92. Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage. In Proceedings of KDD. 1938–1948.
  93. Unlocking Fairness: a Trade-off Revisited. In Advances in Neural Information Processing Systems. 8780–8789.
  94. Counterfactual fairness: Unidentification, bound and algorithm. In Twenty-Eighth International Joint Conference on Artificial Intelligence.
  95. Graph Learning: A Survey. IEEE Transactions on Artificial Intelligence 2, 02 (2021), 109–127. https://doi.org/10.1109/TAI.2021.3076021
  96. Achieving causal fairness through generative adversarial networks. In IJCAI.
  97. Learning fair representations. In International conference on machine learning. 325–333.
  98. Fair Representation Learning for Heterogeneous Information Networks. Proceedings of the International AAAI Conference on Web and Social Media 15, 1 (2021), 877–887.
  99. Fairness in Graph-Based Semi-Supervised Learning. Knowl. Inf. Syst. 65, 2 (2022), 28 pages.
Citations (19)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now