Counterfactual Reciprocal Recommender Systems for User-to-User Matching

2025-08-03

AI Summary

To address popularity bias and feedback loops induced by historical exposure policies in reciprocal recommendation systems (e.g., dating, gaming, talent platforms), this paper proposes the Causal Counterfactual Reciprocal Recommendation (CFRR) framework. CFRR jointly debiases exposure bias from observational logs via inverse propensity weighting and a self-normalized loss function, enabling unbiased learning for bidirectional user matching. Its key innovation lies in systematically integrating causal inference into reciprocal recommendation—explicitly modeling counterfactual exposures to jointly optimize matching accuracy and long-tail fairness. Extensive experiments on multiple real-world datasets demonstrate that CFRR achieves a 3.5% improvement in NDCG@10, increases coverage of long-tail users by 51%, and reduces exposure inequality by 24%, significantly outperforming state-of-the-art debiasing methods.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Reciprocal recommender systems (RRS) in dating, gaming, and talent platforms require mutual acceptance for a match. Logged data, however, over-represents popular profiles due to past exposure policies, creating feedback loops that skew learning and fairness. We introduce Counterfactual Reciprocal Recommender Systems (CFRR), a causal framework to mitigate this bias. CFRR uses inverse propensity scored, self-normalized objectives. Experiments show CFRR improves NDCG@10 by up to 3.5% (e.g., from 0.459 to 0.475 on DBLP, from 0.299 to 0.307 on Synthetic), increases long-tail user coverage by up to 51% (from 0.504 to 0.763 on Synthetic), and reduces Gini exposure inequality by up to 24% (from 0.708 to 0.535 on Synthetic). CFRR offers a promising approach for more accurate and fair user-to-user matching.

Problem

• Mitigates bias in reciprocal recommender systems
• Improves accuracy and fairness in user matching
• Reduces exposure inequality for long-tail users

Innovation

• Uses causal framework to mitigate bias
• Employs inverse propensity scored objectives
• Improves accuracy and fairness in matching