Disentangled Counterfactual Graph Augmentation Framework for Fair Graph Learning with Information Bottleneck
Pages 387 - 405
Abstract
Graph Neural Networks (GNNs) are susceptible to inheriting and even amplifying biases within datasets, subsequently leading to discriminatory decision-making. Our empirical observation reveals that the inconsistent distribution of sensitive attributes conditioned on labels significantly contributes to unfairness. To mitigate this problem, we suggest rectifying this inconsistency of the original dataset through a counterfactual augmentation strategy. Existing methods usually generate counterfactual samples from an entangled representation space, which fail to distinguish the different dependencies on sensitive attributes. Thus, we propose a novel disentangled counterfactual graph augmentation method based on the Information Bottleneck theory, named Fair Disentangled Graph Information Bottleneck (FDGIB). Specifically, FDGIB embeds graphs into two disentangled representation spaces: sensitive-related and sensitive-independent. By satisfying three conditions, FDGIB theoretically guarantees the disentanglement of different sensitive dependencies. We acquire credible counterfactual augmented graphs to facilitate consistency in data distribution and generate fair representations. FDGIB serves as a plug-and-play preprocessing framework that can collaborate with any GNNs. We validate the effectiveness of our model in promoting fairness learning through extensive experiments. Our source code is available at https://github.com/Evanlyf/FDGIB.
References
[1]
Agarwal, C., Lakkaraju, H., Zitnik, M.: Towards a unified framework for fair and stable graph representation learning. In: Uncertainty in Artificial Intelligence, pp. 2114–2124. PMLR (2021)
[2]
Agarwal C, Queen O, Lakkaraju H, and Zitnik M Evaluating explainability for graph neural networks Sci. Data 2023 10 1 144
[3]
Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016)
[4]
Belghazi, M.I., et al.: Mine: mutual information neural estimation. arXiv preprint arXiv:1801.04062 (2018)
[5]
Boratto, L., Fabbri, F., Fenu, G., Marras, M., Medda, G.: Counterfactual graph augmentation for consumer unfairness mitigation in recommender systems. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 3753–3757 (2023)
[6]
Cheng, P., Hao, W., Dai, S., Liu, J., Gan, Z., Carin, L.: Club: a contrastive log-ratio upper bound of mutual information. In: International Conference on Machine Learning, pp. 1779–1788. PMLR (2020)
[7]
Dai, E., Wang, S.: Learning fair graph neural networks with limited and private sensitive attribute information. IEEE Trans. Knowl. Data Eng. (2022)
[8]
Deniz Kose, O., Shen, Y.: Fairgat: Fairness-aware graph attention networks. arXiv e-prints pp. arXiv–2303 (2023)
[9]
Dong, Y., Liu, N., Jalaian, B., Li, J.: Edits: Modeling and mitigating data bias for graph neural networks. In: Proceedings of the ACM Web Conference 2022, pp. 1259–1269 (2022)
[10]
Dong, Y., Wang, S., Ma, J., Liu, N., Li, J.: Interpreting unfairness in graph neural networks via training node attribution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 7441–7449 (2023)
[11]
Du M, Yang F, Zou N, and Hu X Fairness in deep learning: a computational perspective IEEE Intell. Syst. 2020 36 4 25-34
[12]
Feng, S., Wan, H., Wang, N., Luo, M.: Botrgcn: Twitter bot detection with relational graph convolutional networks. In: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 236–239 (2021)
[13]
Guo, S., et al.: Self-supervised spatial-temporal bottleneck attentive network for efficient long-term traffic forecasting. In: 2023 IEEE 39th International Conference on Data Engineering (ICDE), pp. 1585–1596. IEEE (2023)
[14]
Guo, Z., Li, J., Xiao, T., Ma, Y., Wang, S.: Towards fair graph neural networks via graph counterfactual. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 669–678 (2023)
[15]
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural Inform. Process. Systems 30 (2017)
[16]
Hu, J., Wang, C., Lin, X.: Spatio-temporal pyramid networks for traffic forecasting. In: Machine Learning and Knowledge Discovery in Databases: Research Track: European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Proceedings, Part I. (2023).
[17]
Jin, J., Li, H., Feng, F., Ding, S., Wu, P., He, X.: Fairly recommending with social attributes: a flexible and controllable optimization approach. Adv. Neural Inform. Process. Syst. 36 (2024)
[18]
Jordan KL and Freiburger TL The effect of race/ethnicity on sentencing: examining sentence type, jail length, and prison length J. Ethnicity Criminal Justice 2015 13 3 179-196
[19]
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
[20]
Kose, O.D., Shen, Y.: Fair node representation learning via adaptive data augmentation. arXiv preprint arXiv:2201.08549 (2022)
[21]
Kumar S, Mallik A, Khetarpal A, and Panda B Influence maximization in social networks using graph embedding and graph neural network Inf. Sci. 2022 607 1617-1636
[22]
Li H, Wang X, Zhang Z, Yuan Z, Li H, and Zhu W Disentangled contrastive learning on graphs Adv. Neural. Inf. Process. Syst. 2021 34 21872-21884
[23]
Lin, X., Kang, J., Cong, W., Tong, H.: Bemap: Balanced message passing for fair graph neural network. arXiv preprint arXiv:2306.04107 (2023)
[24]
Ling, H., Jiang, Z., Luo, Y., Ji, S., Zou, N.: Learning fair graph representations via automated data augmentations. In: The Eleventh International Conference on Learning Representations (2022)
[25]
Ma, J., Cui, P., Kuang, K., Wang, X., Zhu, W.: Disentangled graph convolutional networks. In: International Conference on Machine Learning, pp. 4212–4221. PMLR (2019)
[26]
Ma, J., Guo, R., Wan, M., Yang, L., Zhang, A., Li, J.: Learning fair node representations with graph counterfactual fairness. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 695–703 (2022)
[27]
Pham, D., Zhang, Y.: Counterfactual based reinforcement learning for graph neural networks. Ann. Oper. Res. 1–17 (2022).
[28]
Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics/0004057 (2000)
[29]
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
[30]
Wang, X., Chen, H., Tang, S., Wu, Z., Zhu, W.: Disentangled representation learning. arXiv preprint arXiv:2211.11695 (2022)
[31]
Wang, Y., Zhao, Y., Dong, Y., Chen, H., Li, J., Derr, T.: Improving fairness in graph neural networks via mitigating sensitive attribute leakage. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1938–1948 (2022)
[32]
Weilbach, C.D., Harvey, W., Wood, F.: Graphically structured diffusion models. In: International Conference on Machine Learning, pp. 36887–36909 (2023)
[33]
Wu, J., et al.: Disenkgat: knowledge graph embedding with disentangled graph attention network. In: Proceedings of the 30th ACM International Conference on Information and Knowledge Management, pp. 2140–2149 (2021)
[34]
Wu, L., Chen, L., Shao, P., Hong, R., Wang, X., Wang, M.: Learning fair representations for recommendation: a graph-based perspective. In: Proceedings of the Web Conference 2021, pp. 2198–2208 (2021)
[35]
Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.i., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. In: International Conference on Machine Learning, pp. 5453–5462. PMLR (2018)
[36]
Zhang, W., Zhang, L., Pfoser, D., Zhao, L.: Disentangled dynamic graph deep generation. In: Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), pp. 738–746. SIAM (2021)
[37]
Zhao H and Gordon GJ Inherent tradeoffs in learning fair representations J. Mach. Learn. Res. 2022 23 1 2527-2552
[38]
Zhao Q, Wu Z, Zhang Z, and Zhou J Koutra D, Plant C, Gomez Rodriguez M, Baralis E, and Bonchi F Long-tail augmented graph contrastive learning for recommendation Machine Learning and Knowledge Discovery in Databases: Research Track: European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Proceedings, Part IV 2023 Cham Springer Nature Switzerland 387-403
Index Terms
- Disentangled Counterfactual Graph Augmentation Framework for Fair Graph Learning with Information Bottleneck
Index terms have been assigned to the content through auto-classification.
Recommendations
β-CapsNet: learning disentangled representation for CapsNet by information bottleneck
AbstractWe present a framework for learning disentangled representation of CapsNet by information bottleneck constraint that distills information into a compact form and motivates to learn an interpretable capsule. In our β-CapsNet framework, the ...
Contrastive learning for fair graph representations via counterfactual graph augmentation
AbstractGraph neural networks (GNNs) have exhibited excellent performance in graph representation learning. However, GNNs might inherit biases from the data, leading to discriminatory predictions. Existing study mainly concentrates on attaining fairness ...
Information bottleneck and selective noise supervision for zero-shot learning
AbstractZero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen classes. Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration deviation ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Sep 2024
513 pages
ISBN:978-3-031-70340-9
DOI:10.1007/978-3-031-70341-6
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 08 September 2024
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Mar 2025