Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation
This addresses fairness and privacy issues in federated learning for recommendation systems, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of achieving gender fairness in federated recommendation systems under strict privacy constraints, proposing Privacy-Preserving Orthogonal Aggregation (PPOA) which improves recommendation effectiveness by up to 8.25% for females and 6.36% for males with a maximum overall improvement of 7.30% while maintaining optimal fairness.
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.