Sharpness-Aware Cross-Domain Recommendation to Cold-Start Users

TL;DR

This paper introduces Sharpness-Aware CDR (SCDR), a novel transfer learning approach for cross-domain recommendation that improves cold-start user recommendations by optimizing for loss sharpness, leading to better generalization and robustness.

Contribution

The paper proposes SCDR, a new method that incorporates loss sharpness into training for cross-domain recommendation, addressing limitations of existing methods that rely on few overlapping users.

Findings

SCDR outperforms existing CDR models on real-world datasets.

SCDR enhances robustness to adversarial attacks.

Theoretical guarantees support improved generalization.

Abstract

Cross-Domain Recommendation (CDR) is a promising paradigm inspired by transfer learning to solve the cold-start problem in recommender systems. Existing state-of-the-art CDR methods train an explicit mapping function to transfer the cold-start users from a data-rich source domain to a target domain. However, a limitation of these methods is that the mapping function is trained on overlapping users across domains, while only a small number of overlapping users are available for training. By visualizing the loss landscape of the existing CDR model, we find that training on a small number of overlapping users causes the model to converge to sharp minima, leading to poor generalization. Based on this observation, we leverage loss-geometry-based machine learning approach and propose a novel CDR method called Sharpness-Aware CDR (SCDR). Our proposed method simultaneously optimizes recommendation loss and loss sharpness, leading to better generalization with theoretical guarantees. Empirical studies on real-world datasets demonstrate that SCDR significantly outperforms the other CDR models for cold-start recommendation tasks, while concurrently enhancing the model's robustness to adversarial attacks.