Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users

TL;DR

This paper addresses fairness in cross-domain recommender systems by generating virtual users for non-overlapping users, improving fairness without sacrificing overall accuracy across multiple datasets and models.

Contribution

It introduces a novel, model-agnostic method that synthesizes virtual user embeddings to mitigate bias against non-overlapping users in CDR.

Findings

Effectively reduces non-overlapping user bias

Maintains overall recommendation accuracy

Demonstrates robustness across datasets and models

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.