Abstract
Algorithmic fairness has been of great interest in the machine learning community and more recently in the graph context. In this paper, we address the problem of dyadic fairness where the task at hand is edge prediction, and the population of interest (nodes) is divided into a protected and a non-protected group, e.g. men and women. The goal is then to ensure that there should be no statistically significant difference in the prediction outcomes between the two groups, after accounting for any relevant factors that may impact the outcome. To proceed, we design a novel loss based on the variational information bottleneck principle to learn individual node representation while controlling a given level of dyadic fairness. The optimization of the loss is done with a Graph Neural Network. Experiments carried out on several real-world datasets confirmed the capacity of the proposed method, to maintain high accuracy on the edge prediction task while significantly reducing potential bias.
This work was partially funded by the French National Research Agency (ANR) in the context of the FAMOUS project.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
see https://github.com/AntoineGourru/leave for code, and experimental details..
- 2.
- 3.
References
Adamic, L.A., Glance, N.: The political blogosphere and the 2004 us election: divided they blog. In: International Workshop on Link Discovery, pp. 36–43 (2005)
Agarwal, C., Lakkaraju, H., Zitnik, M.: Towards a unified framework for fair and stable graph representation learning. In: UAI, pp. 2114–2124. PMLR (2021)
Alemi, A., Fischer, I., Dillon, J., Murphy, K.: Deep variational information bottleneck. In: International Conference on Learning Representations (2017)
Bose, A., Hamilton, W.: Compositional fairness constraints for graph embeddings. In: ICML, pp. 715–724 (2019)
Buyl, M., Bie, T.D.: Debayes: a bayesian method for debiasing network embeddings. In: International Conference on Machine Learning, pp. 2537–2546 (2020)
Buyl, M., Bie, T.D.: The kl-divergence between a graph model and its fair i-projection as a fairness regularizer. In: ECML-PKDD, pp. 351–366 (2021)
Choudhary, M., Laclau, C., Largeron, C.: A survey on fairness for machine learning on graphs (2022). https://arxiv.org/abs/2205.05396
Current, S., He, Y., Gurukar, S., Parthasarathy, S.: Fairegm: fair link prediction and recommendation via emulated graph modification. In: EAAMO (2022)
Dai, E., Wang, S.: Say no to the discrimination: learning fair graph neural networks with limited sensitive attribute information. In: WSDM, pp. 680–688 (2021)
Dong, Y., Liu, N., Jalaian, B., Li, J.: EDITS: modeling and mitigating data bias for graph neural networks. In: Web Conference, pp. 1259–1269 (2022)
Dong, Y., Ma, J., Wang, S., Chen, C., Li, J.: Fairness in graph mining: a survey. IEEE Trans. Knowl. Data Eng. 35(10), 10583–10602 (2023)
Fisher, J., Mittal, A., Palfrey, D., Christodoulopoulos, C.: Debiasing knowledge graph embeddings. In: Proceedings of EMNLP, pp. 7332–7345 (2020)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of ACM SIGKDD KDD, pp. 855–864 (2016)
Hofstra, B., Corten, R., Van Tubergen, F., Ellison, N.B.: Sources of segregation in social networks: a novel approach using facebook. Am. Sociol. Rev. 82(3), 625–656 (2017)
Kang, B., Lijffijt, J., De Bie, T.: Conditional network embeddings. In: ICLR (2019)
Khajehnejad, A., Khajehnejad, M., Babaei, M., Gummadi, K.P., Weller, A., Mirzasoleiman, B.: Crosswalk: fairness-enhanced node representation learning. AAAI 36(11), 11963–11970 (2022)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. Proceedings of the International Conference on Learning Representations (ICLR) (2014)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)
Laclau, C., Redko, I., Choudhary, M., Largeron, C.: All of the fairness for edge prediction with optimal transport. In: AISTATS, pp. 1774–1782. PMLR (2021)
Li, P., Wang, Y., Zhao, H., Hong, P., Liu, H.: On dyadic fairness: Exploring and mitigating bias in graph connections. In: ICLR (2021)
Li, Y., Wang, X., Ning, Y., Wang, H.: FairLP: towards fair link prediction on social network graphs. Proc. Int. AAAI Conf. Web Soc. Media 16, 628–639 (2022)
Masrour, F., Wilson, T., Yan, H., Tan, P., Esfahanian, A.: Bursting the filter bubble: fairness-aware network link prediction. AAAI 34(01), 841–848 (2020)
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. 54(6), 1–35 (2021)
Newman, M.E.J.: Mixing patterns in networks. Phys. Rev. E 67(2) (2003). https://doi.org/10.1103/physreve.67.026126
Oh, S.J., Murphy, K.P., Pan, J., Roth, J., Schroff, F., Gallagher, A.C.: Modeling uncertainty with hedged instance embeddings. In: ICLR (2018)
Oneto, L., Navarin, N., Donini, M.: Learning deep fair graph neural networks. In: European Symposium on Artificial Neural Networks, pp. 31–36 (2020)
Palowitch, J., Perozzi, B.: Monet: debiasing graph embeddings via the metadata-orthogonal training unit. In: ASONAM (2020)
Rahman, T.A., Surma, B., Backes, M., Zhang, Y.: Fairwalk: Towards fair graph embedding. In: IJCAI, pp. 3289–3295 (2019)
Rozemberczki, B., Allen, C., Sarkar, R.: Multi-scale attributed node embedding. J. Complex Netw. 9(2), cnab014 (2021)
Rozemberczki, B., Sarkar, R.: Characteristic functions on graphs: birds of a feather, from statistical descriptors to parametric models. In: CIKM, pp. 1325–1334 (2020)
Saxena, A., Fletcher, G., Pechenizkiy, M.: Fairsna: algorithmic fairness in social network analysis (2022). https://arxiv.org/abs/2209.01678
Spinelli, I., Scardapane, S., Hussain, A., Uncini, A.: Fairdrop: biased edge dropout for enhancing fairness in graph representation learning. In: TAI (2021)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Wang, N., Lin, L., Li, J., Wang, H.: Unbiased graph embedding with biased graph observations. In: Web Conference, pp. 1423–1433 (2022)
Wang, Y., Zhao, Y., Dong, Y., Chen, H., Li, J., Derr, T.: Improving fairness in graph neural networks via mitigating sensitive attribute leakage. In: KDD (2022)
Zhang, T., et al.: Fairness in graph-based semi-supervised learning. Knowl. Inf. Syst. 65(2), 543–570 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gourru, A., Laclau, C., Choudhary, M., Largeron, C. (2024). Variational Perspective on Fair Edge Prediction. In: Miliou, I., Piatkowski, N., Papapetrou, P. (eds) Advances in Intelligent Data Analysis XXII. IDA 2024. Lecture Notes in Computer Science, vol 14641. Springer, Cham. https://doi.org/10.1007/978-3-031-58547-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-58547-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-58546-3
Online ISBN: 978-3-031-58547-0
eBook Packages: Computer ScienceComputer Science (R0)