TY - GEN
T1 - Towards Fair Federated Recommendation Learning
T2 - 16th ACM Conference on Recommender Systems, RecSys 2022
AU - Maeng, Kiwan
AU - Lu, Haiyu
AU - Melis, Luca
AU - Nguyen, John
AU - Rabbat, Mike
AU - Wu, Carole Jean
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/9/12
Y1 - 2022/9/12
N2 - Federated learning (FL) is an effective mechanism for data privacy in recommender systems that runs machine learning model training on-device. While prior FL optimizations tackled the data and system heterogeneity challenges, they assume the two are independent of each other. This fundamental assumption is not reflective of real-world, large-scale recommender systems-data and system heterogeneity are tightly intertwined. This paper takes a data-driven approach to show the inter-dependence of data and system heterogeneity in real-world data and quantifies its impact on the overall model quality and fairness. We design a framework, RF2, to model the inter-dependence and evaluate its impact on state-of-the-art model optimization techniques for federated recommendation tasks. We demonstrate that the impact on fairness can be severe under realistic heterogeneity scenarios, by up to 15.8-41 × compared to a simple setup assumed in most (if not all) prior work. The result shows that modeling realistic system-induced data heterogeneity is essential to achieving fair federated recommendation learning.
AB - Federated learning (FL) is an effective mechanism for data privacy in recommender systems that runs machine learning model training on-device. While prior FL optimizations tackled the data and system heterogeneity challenges, they assume the two are independent of each other. This fundamental assumption is not reflective of real-world, large-scale recommender systems-data and system heterogeneity are tightly intertwined. This paper takes a data-driven approach to show the inter-dependence of data and system heterogeneity in real-world data and quantifies its impact on the overall model quality and fairness. We design a framework, RF2, to model the inter-dependence and evaluate its impact on state-of-the-art model optimization techniques for federated recommendation tasks. We demonstrate that the impact on fairness can be severe under realistic heterogeneity scenarios, by up to 15.8-41 × compared to a simple setup assumed in most (if not all) prior work. The result shows that modeling realistic system-induced data heterogeneity is essential to achieving fair federated recommendation learning.
UR - http://www.scopus.com/inward/record.url?scp=85139569130&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85139569130&partnerID=8YFLogxK
U2 - 10.1145/3523227.3546759
DO - 10.1145/3523227.3546759
M3 - Conference contribution
AN - SCOPUS:85139569130
T3 - RecSys 2022 - Proceedings of the 16th ACM Conference on Recommender Systems
SP - 156
EP - 167
BT - RecSys 2022 - Proceedings of the 16th ACM Conference on Recommender Systems
PB - Association for Computing Machinery, Inc
Y2 - 18 September 2022 through 23 September 2022
ER -