A Dual-Adversarial Learning Framework with Explicit Constraints for Two-Sided Fairness in Recommendation System
Open Access
- 1 January 2026
- journal article
- research article
- Published by Walter de Gruyter GmbH in Open Information Science
- Vol. 10 (1)
Abstract
Recommendation systems frequently exhibit two fundamental types of bias: user-side bias, where recommendations discriminate based on protected attributes such as gender, and item-side bias, where popular items dominate exposure irrespective of their actual relevance or quality. To address both simultaneously, we propose a dual-adversarial framework with two discriminators: a user-gender discriminator designed to mitigate gender bias by removing sensitive information from user embeddings, and an item-popularity discriminator aimed at reducing popularity bias among items. While adversarial learning encourages the model to generate bias-free embeddings by fooling discriminators, residual sensitive information may persist due to imperfect discriminator inference and distributional discrepancies. To further reduce this residual bias and enforce balanced, fair recommendations, we enhance the dual adversarial learning framework with two explicit fairness constraints that operate on the learned debiased user and item embeddings: an individual user fairness constraint that guarantees equitable recommendations for users with similar preferences, and a popularity regularization term that balances exposure across popular and less popular item groups. Experiments on three real-world datasets (MovieLens 1M, MovieLens 100K, and Book-Crossing) demonstrate significant gender predictability drops and popularity skew decreases, while maintaining competitive recommendation quality.Keywords
This publication has 29 references indexed in Scilit:
- Recommender Systems and Discrimination2023
- Revisiting Popularity and Demographic Biases in Recommender Evaluation and Effectiveness2022
- Interplay between upsampling and regularization for provider fairness in recommender systemsUser Modeling and User-Adapted Interaction, 2021
- iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making2019
- Equity of Attention2018
- Controlling Popularity Bias in Learning-to-Rank Recommendation2017
- Wide & Deep Learning for Recommender Systems2016
- Pairwise preference regression for cold-start recommendation2009
- Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensionsIEEE Transactions on Knowledge and Data Engineering, 2005
- Bias in computer systemsACM Transactions on Information Systems, 1996