Aligning Performance with Contribution: Towards Contribution-Aware Fair Recommendation

2026-10-06

AI Summary

This study addresses the inequitable distribution mechanisms in recommender systems, where user contributions and benefits are misaligned, thereby undermining incentives for sustained participation. To this end, it proposes a novel “contribution-performance fairness” perspective and introduces the CPFR framework. Methodologically, this work pioneers an alignment-based fairness mechanism grounded in estimated user contributions, establishing dual constraints of inter-group alignment and intra-group fairness. Ordered user cohorts are constructed via interaction volume, loss alignment, and optimization intensity, while game-theoretic analysis is leveraged to reinforce contribution incentives and jointly optimize recommendation accuracy and fairness metrics. Experiments conducted across three datasets and multiple models demonstrate that the proposed approach achieves a superior trade-off between accuracy and fairness, effectively enhancing system-level recommendation performance.

Abstract

Existing research on user fairness in recommender systems has developed diverse objectives. However, it has paid limited attention to a distinct distributive perspective: whether users' contributions to model learning should be reflected in the recommendation benefits they receive. We argue that, in addition to existing fairness protections, a fair system may account for the alignment between users' estimated contributions and the recommendation performance they receive. Such alignment can incentivize sustained and informative engagement, thereby supporting a sustainable recommendation ecosystem. To this end, we propose Contribution-Performance Fairness, a novel fairness perspective which requires recommendation performance to be aligned with estimated contribution across user groups and to remain equitable among users with comparable contributions within a same group. To instantiate this perspective, we introduce the Contribution-Performance Fair Recommender (CPFR), a framework applicable to different backbone recommenders. CPFR constructs ordered user groups from a training-dependent contribution considering interaction volume, loss alignment, and optimization intensity, and jointly optimizes recommendation accuracy with the two fairness requirements. A game-theoretic analysis shows that such alignment can strengthen contribution incentives and improve system-level recommendation accuracy under voluntary contribution. Experiments on three datasets and three backbone models demonstrate that CPFR achieves a strong accuracy--fairness trade-off under the proposed operational metric.

Problem

• recommender systems
• user fairness
• contribution-performance alignment
• distributive fairness
• recommendation ecosystem

Innovation

• Contribution-Performance Fairness
• Fair Recommendation
• Game-Theoretic Analysis
• User Contribution Alignment
• CPFR