Cross-Domain Sequential Recommendation via Neural Process

TL;DR

This paper introduces a novel approach to cross-domain sequential recommendation that effectively leverages both overlapped and non-overlapped user behaviors, overcoming limitations of existing methods that rely heavily on overlapped users.

Contribution

The paper proposes a neural process-based model that captures cross-domain user preferences without depending solely on overlapped users, enabling better utilization of non-overlapped user data.

Findings

Outperforms existing CDSR methods on multiple datasets.

Effectively models non-overlapped user behaviors.

Enhances recommendation accuracy across domains.

Abstract

Cross-Domain Sequential Recommendation (CDSR) is a hot topic in sequence-based user interest modeling, which aims at utilizing a single model to predict the next items for different domains. To tackle the CDSR, many methods are focused on domain overlapped users' behaviors fitting, which heavily relies on the same user's different-domain item sequences collaborating signals to capture the synergy of cross-domain item-item correlation. Indeed, these overlapped users occupy a small fraction of the entire user set only, which introduces a strong assumption that the small group of domain overlapped users is enough to represent all domain user behavior characteristics. However, intuitively, such a suggestion is biased, and the insufficient learning paradigm in non-overlapped users will inevitably limit model performance. Further, it is not trivial to model non-overlapped user behaviors in CDSR because there are no other domain behaviors to collaborate with, which causes the observed single-domain users' behavior sequences to be hard to contribute to cross-domain knowledge mining. Considering such a phenomenon, we raise a challenging and unexplored question: How to unleash the potential of non-overlapped users' behaviors to empower CDSR?