{"ID":2891482,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17749","arxiv_id":"2507.17749","title":"Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users","abstract":"Cross-domain recommendation (CDR) methods predominantly leverage overlapping users to transfer knowledge from a source domain to a target domain. However, through empirical studies, we uncover a critical bias inherent in these approaches: while overlapping users experience significant enhancements in recommendation quality, non-overlapping users benefit minimally and even face performance degradation. This unfairness may erode user trust, and, consequently, negatively impact business engagement and revenue. To address this issue, we propose a novel solution that generates virtual source-domain users for non-overlapping target-domain users. Our method utilizes a dual attention mechanism to discern similarities between overlapping and non-overlapping users, thereby synthesizing realistic virtual user embeddings. We further introduce a limiter component that ensures the generated virtual users align with real-data distributions while preserving each user's unique characteristics. Notably, our method is model-agnostic and can be seamlessly integrated into any CDR model. Comprehensive experiments conducted on three public datasets with five CDR baselines demonstrate that our method effectively mitigates the CDR non-overlapping user bias, without loss of overall accuracy. Our code is publicly available at https://github.com/WeixinChen98/VUG.","short_abstract":"Cross-domain recommendation (CDR) methods predominantly leverage overlapping users to transfer knowledge from a source domain to a target domain. However, through empirical studies, we uncover a critical bias inherent in these approaches: while overlapping users experience significant enhancements in recommendation qua...","url_abs":"https://arxiv.org/abs/2507.17749","url_pdf":"https://arxiv.org/pdf/2507.17749v1","authors":"[\"Weixin Chen\",\"Yuhan Zhao\",\"Li Chen\",\"Weike Pan\"]","published":"2025-07-23T17:59:08Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false,"code_links":[{"ID":611886,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891482,"paper_url":"https://arxiv.org/abs/2507.17749","paper_title":"Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users","repo_url":"https://github.com/WeixinChen98/VUG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}