Papers
Topics
Authors
Recent
Search
2000 character limit reached

Towards Fairness in Provably Communication-Efficient Federated Recommender Systems

Published 3 May 2024 in cs.IR, cs.HC, and cs.LG | (2405.15788v1)

Abstract: To reduce the communication overhead caused by parallel training of multiple clients, various federated learning (FL) techniques use random client sampling. Nonetheless, ensuring the efficacy of random sampling and determining the optimal number of clients to sample in federated recommender systems (FRSs) remains challenging due to the isolated nature of each user as a separate client. This challenge is exacerbated in models where public and private features can be separated, and FL allows communication of only public features (item gradients). In this study, we establish sample complexity bounds that dictate the ideal number of clients required for improved communication efficiency and retained accuracy in such models. In line with our theoretical findings, we empirically demonstrate that RS-FairFRS reduces communication cost (~47%). Second, we demonstrate the presence of class imbalance among clients that raises a substantial equity concern for FRSs. Unlike centralized machine learning, clients in FRS can not share raw data, including sensitive attributes. For this, we introduce RS-FairFRS, first fairness under unawareness FRS built upon random sampling based FRS. While random sampling improves communication efficiency, we propose a novel two-phase dual-fair update technique to achieve fairness without revealing protected attributes of active clients participating in training. Our results on real-world datasets and different sensitive features illustrate a significant reduction in demographic bias (~approx40\%), offering a promising path to achieving fairness and communication efficiency in FRSs without compromising the overall accuracy of FRS.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (70)
  1. Gediminas Adomavicius and Alexander Tuzhilin. 2005. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE transactions on knowledge and data engineering 17, 6 (2005), 734–749.
  2. No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation. arXiv:2312.10080 [cs.IR]
  3. A federated learning approach for privacy protection in context-aware recommender systems. Comput. J. 64, 7 (2021), 1016–1027.
  4. Convergence of update aware device scheduling for federated learning at the wireless edge. IEEE Transactions on Wireless Communications 20, 6 (2021), 3643–3658.
  5. Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System. CoRR abs/1901.09888 (2019). arXiv:1901.09888 http://arxiv.org/abs/1901.09888
  6. Diverse Client Selection for Federated Learning via Submodular Maximization. In International Conference on Learning Representations. https://openreview.net/forum?id=nwKXyFvaUm
  7. Fairness in Recommendation Ranking through Pairwise Comparisons. CoRR abs/1903.00780 (2019). arXiv:1903.00780 http://arxiv.org/abs/1903.00780
  8. Deepfair: deep learning for improving fairness in recommender systems. arXiv preprint arXiv:2006.05255 (2020).
  9. Hans-Hermann Bock. 2007. Clustering methods: a history of k-means algorithms. Selected contributions in data analysis and classification (2007), 161–172.
  10. Krista Bradford. 2022. Google shows men ads for Better Jobs. https://tgsus.com/diversity/google-shows-men-ads-for-better-jobs/
  11. On Large-Cohort Training for Federated Learning. CoRR abs/2106.07820 (2021). arXiv:2106.07820 https://arxiv.org/abs/2106.07820
  12. Neural collaborative reasoning. In Proceedings of the Web Conference 2021. 1516–1527.
  13. Optimal Client Sampling for Federated Learning. CoRR abs/2010.13723 (2020). arXiv:2010.13723 https://arxiv.org/abs/2010.13723
  14. Optimal Client Sampling for Federated Learning. Transactions on Machine Learning Research (2022). https://openreview.net/forum?id=8GvRCWKHIL
  15. Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies. CoRR abs/2010.01243 (2020). arXiv:2010.01243 https://arxiv.org/abs/2010.01243
  16. Towards understanding biased client selection in federated learning. In International Conference on Artificial Intelligence and Statistics. PMLR, 10351–10375.
  17. Emergent unfairness in algorithmic fairness-accuracy trade-off research. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society. 46–54.
  18. FaiRecSys: mitigating algorithmic bias in recommender systems. International Journal of Data Science and Analytics 9, 2 (2020), 197–213.
  19. Clustered Sampling: Low-Variance and Improved Representativity for Clients Selsection in Federated Learning. CoRR abs/2105.05883 (2021). arXiv:2105.05883 https://arxiv.org/abs/2105.05883
  20. On The Impact of Client Sampling on Federated Learning Convergence. CoRR abs/2107.12211 (2021). arXiv:2107.12211 https://arxiv.org/abs/2107.12211
  21. Client Selection in Federated Learning: Principles, Challenges, and Opportunities. IEEE Internet of Things Journal 10, 24 (2023), 21811–21819. https://doi.org/10.1109/JIOT.2023.3299573
  22. Fairness-aware explainable recommendation over knowledge graphs. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 69–78.
  23. Toward Pareto efficient fairness-utility trade-off in recommendation through reinforcement learning. In Proceedings of the fifteenth ACM international conference on web search and data mining. 316–324.
  24. GroupLens. 2021. Movielens 1M Dataset. https://grouplens.org/datasets/movielens/1m/
  25. Movie recommender system using collaborative filtering. In 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE, 415–420.
  26. Deeprec: On-device deep learning for privacy-preserving sequential recommendation in mobile commerce. In Proceedings of the Web Conference 2021. 900–911.
  27. Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web. 173–182.
  28. Clustering and inertia: structural integration of home care in Swedish elderly care. International Journal of Integrated Care 7 (2007).
  29. Fair Federated Learning via Bounded Group Loss. https://doi.org/10.48550/ARXIV.2203.10190
  30. Collaborative Filtering for Implicit Feedback Datasets. In 2008 Eighth IEEE International Conference on Data Mining. 263–272. https://doi.org/10.1109/ICDM.2008.22
  31. Springboard India. 2019. How netflix’s recommendation Engine Works? https://medium.com/@springboard_ind/how-netflixs-recommendation-engine-works-bd1ee381bf81
  32. Mitigating demographic biases in social media-based recommender systems. KDD (Social Impact Track) (2019).
  33. Recommender systems: an introduction. Cambridge University Press.
  34. F3: Fair and Federated Face Attribute Classification with Heterogeneous Data. In The 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) (2023-05-25).
  35. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37.
  36. Oort: Efficient federated learning via guided participant selection. In 15th {{\{{USENIX}}\}} Symposium on Operating Systems Design and Implementation ({{\{{OSDI}}\}} 21). 19–35.
  37. Exploring Cross-group Discrepancies in Calibrated Popularity for Accuracy/Fairness Trade-off Optimization.. In MORS@ RecSys.
  38. PyramidFL: A fine-grained client selection framework for efficient federated learning. In Proceedings of the 28th Annual International Conference on Mobile Computing And Networking. 158–171.
  39. User-oriented fairness in recommendation. In Proceedings of the Web Conference 2021. 624–632.
  40. FedRec: Federated Recommendation With Explicit Feedback. IEEE Intelligent Systems 36, 5 (2021), 21–30. https://doi.org/10.1109/MIS.2020.3017205
  41. Tackling system and statistical heterogeneity for federated learning with adaptive client sampling. In IEEE INFOCOM 2022-IEEE conference on computer communications. IEEE, 1739–1748.
  42. Towards communication efficient and fair federated personalized sequential recommendation. arXiv preprint arXiv:2208.10692 (2022).
  43. Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity. In Proceedings of the 16th ACM Conference on Recommender Systems (Seattle, WA, USA) (RecSys ’22). Association for Computing Machinery, New York, NY, USA, 156–167. https://doi.org/10.1145/3523227.3546759
  44. Federated Learning with Server Learning: Enhancing Performance for Non-IID Data. CoRR abs/2210.02614 (2022). https://doi.org/10.48550/arXiv.2210.02614 arXiv:2210.02614
  45. Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization. CoRR abs/2201.11066 (2022). arXiv:2201.11066 https://arxiv.org/abs/2201.11066
  46. Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv:1602.05629 [cs.LG]
  47. Christie Natashia. 2023. Recommendation system with matrix factorization. https://towardsdatascience.com/recommendation-system-with-matrix-factorization-ebc4736869e4
  48. Fast-convergent federated learning. IEEE Journal on Selected Areas in Communications 39, 1 (2020), 201–218.
  49. Takayuki Nishio and Ryo Yonetani. 2019. Client selection for federated learning with heterogeneous resources in mobile edge. In ICC 2019-2019 IEEE international conference on communications (ICC). IEEE, 1–7.
  50. Minimax Demographic Group Fairness in Federated Learning. CoRR abs/2201.08304 (2022). arXiv:2201.08304 https://arxiv.org/abs/2201.08304
  51. Measuring discrimination in socially-sensitive decision records. In Proceedings of the 2009 SIAM international conference on data mining. SIAM, 581–592.
  52. Vasileios Perifanis and Pavlos S Efraimidis. 2022. Federated neural collaborative filtering. Knowledge-Based Systems 242 (2022), 108441.
  53. Neural collaborative filtering vs. matrix factorization revisited. In Proceedings of the 14th ACM Conference on Recommender Systems. 240–248.
  54. Federated learning under intermittent client availability and time-varying communication constraints. IEEE Journal of Selected Topics in Signal Processing 17, 1 (2022), 98–111.
  55. Nasim Sonboli. 2022. Controlling the Fairness/Accuracy Tradeoff in Recommender Systems. Ph. D. Dissertation. University of Colorado at Boulder.
  56. Personalized Federated Learning with Server-Side Information. https://doi.org/10.48550/ARXIV.2205.11044
  57. Eiffel: Efficient and fair scheduling in adaptive federated learning. IEEE Transactions on Parallel and Distributed Systems 33, 12 (2022), 4282–4294.
  58. Sheridan Wall. 2021. LinkedIn’s job-matching AI was biased. the company’s solution? more AI. https://www.technologyreview.com/2021/06/23/1026825/linkedin-ai-bias-ziprecruiter-monster-artificial-intelligence
  59. A federated graph neural network framework for privacy-preserving personalization. Nature Communications 13, 1 (2022), 1–10.
  60. A federated graph neural network framework for privacy-preserving personalization. Nature Communications 13, 1 (2022), 3091.
  61. Fairness-aware group recommendation with pareto-efficiency. In Proceedings of the Eleventh ACM Conference on Recommender Systems. 107–115.
  62. Jie Xu and Heqiang Wang. 2020. Client selection and bandwidth allocation in wireless federated learning networks: A long-term perspective. IEEE Transactions on Wireless Communications 20, 2 (2020), 1188–1200.
  63. Causal intersectionality for fair ranking. CoRR abs/2006.08688 (2020). arXiv:2006.08688 https://arxiv.org/abs/2006.08688
  64. Sirui Yao and Bert Huang. 2017. Beyond parity: Fairness objectives for collaborative filtering. Advances in neural information processing systems 30 (2017).
  65. GIFAIR-FL: An Approach for Group and Individual Fairness in Federated Learning. arXiv:2108.02741 [cs.LG]
  66. FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server. https://doi.org/10.48550/ARXIV.2204.11536
  67. A federated recommender system for online learning environments. In Advances in Web-Based Learning-ICWL 2012: 11th International Conference, Sinaia, Romania, September 2-4, 2012. Proceedings 11. Springer, 89–98.
  68. Are you left out? an efficient and fair federated learning for personalized profiles on wearable devices of inferior networking conditions. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, 2 (2022), 1–25.
  69. Federated learning on non-IID data: A survey. Neurocomputing 465 (2021), 371–390.
  70. Cali3F: Calibrated Fast Fair Federated Recommendation System. 2022 International Joint Conference on Neural Networks (IJCNN) (2022), 1–8.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 2 tweets with 0 likes about this paper.

Sign Up for Free