Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

GRAPHGINI: Fostering Individual and Group Fairness in Graph Neural Networks (2402.12937v1)

Published 20 Feb 2024 in cs.LG and cs.SI

Abstract: We address the growing apprehension that GNNs, in the absence of fairness constraints, might produce biased decisions that disproportionately affect underprivileged groups or individuals. Departing from previous work, we introduce for the first time a method for incorporating the Gini coefficient as a measure of fairness to be used within the GNN framework. Our proposal, GRAPHGINI, works with the two different goals of individual and group fairness in a single system, while maintaining high prediction accuracy. GRAPHGINI enforces individual fairness through learnable attention scores that help in aggregating more information through similar nodes. A heuristic-based maximum Nash social welfare constraint ensures the maximum possible group fairness. Both the individual fairness constraint and the group fairness constraint are stated in terms of a differentiable approximation of the Gini coefficient. This approximation is a contribution that is likely to be of interest even beyond the scope of the problem studied in this paper. Unlike other state-of-the-art, GRAPHGINI automatically balances all three optimization objectives (utility, individual, and group fairness) of the GNN and is free from any manual tuning of weight parameters. Extensive experimentation on real-world datasets showcases the efficacy of GRAPHGINI in making significant improvements in individual fairness compared to all currently available state-of-the-art methods while maintaining utility and group equality.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Towards a unified framework for fair and stable graph representation learning. In Uncertainty in Artificial Intelligence. PMLR, 2114–2124.
  2. Graph-based deep learning for medical diagnosis and analysis: past, present and future. Sensors 21, 14 (2021), 4758.
  3. Avishek Bose and William Hamilton. 2019. Compositional Fairness Constraints for Graph Embeddings. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 715–724.
  4. The unreasonable fairness of maximum Nash welfare. ACM Transactions on Economics and Computation (TEAC) 7, 3 (2019), 1–32.
  5. The magic of nash social welfare in optimization: Do not sum, just multiply! The ANZIAM Journal 64, 2 (2022), 119–134.
  6. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794–803.
  7. Camilo Dagum. 1980. The generation and distribution of income, the Lorenz curve and the Gini ratio. Economie appliquée 33, 2 (1980), 327–367.
  8. Enyan Dai and Suhang Wang. 2021. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining.
  9. A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability. arXiv preprint arXiv:2204.08570 (2022).
  10. Jeffrey Dastin. 2022. Amazon scraps secret AI recruiting tool that showed bias against women. In Ethics of data and analytics. Auerbach Publications, 296–299.
  11. Individual fairness for graph neural networks: A ranking based approach. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 300–310.
  12. Fairness in graph mining: A survey. IEEE Transactions on Knowledge and Data Engineering (2023).
  13. Dheeru Dua and Casey Graff. 2017. UCI machine learning repository (2020). URL http://archive. ics. uci. edu/ml (2017).
  14. Fairness through Awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference (Cambridge, Massachusetts) (ITCS ’12). Association for Computing Machinery, New York, NY, USA, 214–226.
  15. Graph neural networks for social recommendation. In The world wide web conference. 417–426.
  16. Equitable allocations of indivisible goods. arXiv preprint arXiv:1905.10656 (2019).
  17. Joseph L Gastwirth. 1972. The estimation of the Lorenz curve and Gini index. The review of economics and statistics (1972), 306–316.
  18. JNET: Learning User Representations via Joint Network Embedding and Topic Embedding. In Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM ’20). Association for Computing Machinery, 205–213.
  19. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  20. Efficient Fair Graph Representation Learning Using a Multi-level Framework. In Companion Proceedings of the ACM Web Conference 2023. 298–301.
  21. InFoRM: Individual Fairness on Graph Mining. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining.
  22. Thomas N. Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. CoRR abs/1609.02907 (2016). arXiv:1609.02907 http://arxiv.org/abs/1609.02907
  23. Oyku Deniz Kose and Yanning Shen. 2022. Fast&fair: Training acceleration and bias mitigation for GNNs. Transactions on Machine Learning Research (2022).
  24. O Deniz Kose and Yanning Shen. 2023. FairGAT: Fairness-aware Graph Attention Networks. arXiv preprint arXiv:2303.14591 (2023).
  25. Operationalizing Individual Fairness with Pairwise Fair Representations. Proc. VLDB Endow. 13, 4 (2020), 506–518.
  26. BeMap: Balanced Message Passing for Fair Graph Neural Network. arXiv preprint arXiv:2306.04107 (2023).
  27. On approximately fair allocations of indivisible goods. In Proceedings of the 5th ACM Conference on Electronic Commerce. 125–131.
  28. Trustworthy ai: A computational perspective. ACM Transactions on Intelligent Systems and Technology 14, 1 (2022), 1–59.
  29. A Survey on Bias and Fairness in Machine Learning. Comput. Surveys 54, 6 (2021).
  30. Fair partitioning of public resources: Redrawing district boundary to minimize spatial inequality in school funding. In Proceedings of the Web Conference 2021. 646–657.
  31. Fairwalk: Towards Fair Graph Embedding. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization.
  32. Linking bank clients using graph neural networks powered by rich transactional data: Extended abstract. In 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA). 787–788.
  33. Thitithep Sitthiyot and Kanyarat Holasut. 2021. A simple method for estimating the Lorenz curve. Humanities and Social Sciences Communications 8, 1 (2021), 1–9.
  34. GUIDE: Group Equality Informed Individual Fairness in Graph Neural Networks. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD ’22). Association for Computing Machinery, New York, NY, USA, 1625–1634.
  35. Lubos Takac and Michal Zabovsky. 2012a. Data analysis in public social networks. International Scientific Conference and International Workshop Present Day Trends of Innovations 1 (2012), 1–6.
  36. Lubos Takac and Michal Zabovsky. 2012b. Data analysis in public social networks. In International scientific conference and international workshop present day trends of innovations, Vol. 1.
  37. Graph attention networks. stat 1050, 20 (2017), 10–48550.
  38. A Semi-Supervised Graph Attentive Network for Financial Fraud Detection. In 2019 IEEE International Conference on Data Mining (ICDM). 598–607. https://doi.org/10.1109/ICDM.2019.00070
  39. CurGraph: Curriculum Learning for Graph Classification. In Proceedings of the Web Conference 2021. Association for Computing Machinery, 1238–1248.
  40. How Powerful are Graph Neural Networks? CoRR abs/1810.00826 (2018). arXiv:1810.00826 http://arxiv.org/abs/1810.00826
  41. Representation Learning on Graphs with Jumping Knowledge Networks. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). 5453–5462.
  42. I-Cheng Yeh and Che-hui Lien. 2009. The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert systems with applications 36, 2 (2009), 2473–2480.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Anuj Kumar Sirohi (4 papers)
  2. Anjali Gupta (31 papers)
  3. Sayan Ranu (41 papers)
  4. Sandeep Kumar (143 papers)
  5. Amitabha Bagchi (24 papers)
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets