Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation

TY - GEN

T1 - Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation

AU - Zhang, Siqing

AU - Ding, Yuchen

AU - Tang, Wei

AU - Sun, Wei

AU - Liao, Yong

AU - Zhou, Peng Yuan

N1 - Publisher Copyright: © 2025 Copyright held by the owner/author(s).

PY - 2025/3/10

Y1 - 2025/3/10

N2 - Under stringent privacy constraints, whether federated recommendation systems can achieve group fairness remains an inadequately explored question. Taking gender fairness as a representative issue, we identify three phenomena in federated recommendation systems: performance difference, data imbalance, and preference disparity. We discover that the state-of-the-art methods only focus on the first phenomenon. Consequently, their imposition of inappropriate fairness constraints detrimentally affects the model training. Moreover, due to insufficient sensitive attribute protection of existing works, we can infer the gender of all users with 99.90% accuracy even with the addition of maximal noise. In this work, we propose Privacy-Preserving Orthogonal Aggregation (PPOA), which employs the secure aggregation scheme and quantization technique, to prevent the suppression of minority groups by the majority and preserve the distinct preferences for better group fairness. PPOA can assist different groups in obtaining their respective model aggregation results through a designed orthogonal mapping while keeping their attributes private. Experimental results on three real-world datasets demonstrate that PPOA enhances recommendation effectiveness for both females and males by up to 8.25% and 6.36%, respectively, with a maximum overall improvement of 7.30%, and achieves optimal fairness in most cases. Extensive ablation experiments and visualizations indicate that PPOA successfully maintains preferences for different gender groups.

AB - Under stringent privacy constraints, whether federated recommendation systems can achieve group fairness remains an inadequately explored question. Taking gender fairness as a representative issue, we identify three phenomena in federated recommendation systems: performance difference, data imbalance, and preference disparity. We discover that the state-of-the-art methods only focus on the first phenomenon. Consequently, their imposition of inappropriate fairness constraints detrimentally affects the model training. Moreover, due to insufficient sensitive attribute protection of existing works, we can infer the gender of all users with 99.90% accuracy even with the addition of maximal noise. In this work, we propose Privacy-Preserving Orthogonal Aggregation (PPOA), which employs the secure aggregation scheme and quantization technique, to prevent the suppression of minority groups by the majority and preserve the distinct preferences for better group fairness. PPOA can assist different groups in obtaining their respective model aggregation results through a designed orthogonal mapping while keeping their attributes private. Experimental results on three real-world datasets demonstrate that PPOA enhances recommendation effectiveness for both females and males by up to 8.25% and 6.36%, respectively, with a maximum overall improvement of 7.30%, and achieves optimal fairness in most cases. Extensive ablation experiments and visualizations indicate that PPOA successfully maintains preferences for different gender groups.

KW - Federated Recommendation

KW - Gender Fairness

KW - Sensitive Attribute Preservation

UR - http://www.scopus.com/inward/record.url?scp=105001669544&partnerID=8YFLogxK

U2 - 10.1145/3701551.3703513

DO - 10.1145/3701551.3703513

M3 - Article in proceedings

AN - SCOPUS:105001669544

SP - 327

EP - 335

BT - WSDM 2025 - Proceedings of the 18th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery

CY - New York

T2 - 18th ACM International Conference on Web Search and Data Mining, WSDM 2025

Y2 - 10 March 2025 through 14 March 2025

ER -