LTP-MMF: Towards Long-term Provider Max-min Fairness Under Recommendation Feedback Loops

TL;DR

This paper introduces LTP-MMF, an online ranking model designed to ensure long-term provider fairness in recommender systems affected by feedback loops, with theoretical guarantees and superior long-term performance.

Contribution

The paper proposes LTP-MMF, a novel online ranking model that addresses long-term provider fairness under feedback loops, with proven sub-linear regret bounds and improved long-term results.

Findings

LTP-MMF outperforms baselines in long-term fairness and accuracy.

Theoretical analysis confirms sub-linear regret bounds for LTP-MMF.

Experimental results on public benchmarks validate the effectiveness of the proposed method.

Abstract

Multi-stakeholder recommender systems involve various roles, such as users, and providers. Previous work pointed out that max-min fairness (MMF) is a better metric to support weak providers. However, when considering MMF, the features or parameters of these roles vary over time, how to ensure long-term provider MMF has become a significant challenge. We observed that recommendation feedback loops (named RFL) will greatly influence the provider MMF in the long term. RFL means that recommender systems can only receive feedback on exposed items from users and update recommender models incrementally based on this feedback. When utilizing the feedback, the recommender model will regard the unexposed items as negative. In this way, the tail provider will not get the opportunity to be exposed, and its items will always be considered negative samples. Such phenomena will become more and more serious in RFL. To alleviate the problem, this paper proposes an online ranking model named Long-Term Provider Max-min Fairness (named LTP-MMF). Theoretical analysis shows that the long-term regret of LTP-MMF enjoys a sub-linear bound. Experimental results on three public recommendation benchmarks demonstrated that LTP-MMF can outperform the baselines in the long term.