A Unified Framework for Cross-Domain Recommendation

TL;DR

This paper introduces UniCDR+, an extended framework for cross-domain recommendation that adapts to multiple scenarios, improving prediction accuracy by leveraging transfer learning and addressing data sparsity and cold-start issues.

Contribution

We extend the state-of-the-art UniCDR model to UniCDR+ for better adaptability across diverse CDR scenarios, inspired by domain-invariant transfer learning.

Findings

Successfully deployed on Kuaishou Living-Room RecSys

Enhanced performance across various CDR scenarios

Addresses data sparsity and cold-start challenges

Abstract

In addressing the persistent challenges of data-sparsity and cold-start issues in domain-expert recommender systems, Cross-Domain Recommendation (CDR) emerges as a promising methodology. CDR aims at enhancing prediction performance in the target domain by leveraging interaction knowledge from related source domains, particularly through users or items that span across multiple domains (e.g., Short-Video and Living-Room). For academic research purposes, there are a number of distinct aspects to guide CDR method designing, including the auxiliary domain number, domain-overlapped element, user-item interaction types, and downstream tasks. With so many different CDR combination scenario settings, the proposed scenario-expert approaches are tailored to address a specific vertical CDR scenario, and often lack the capacity to adapt to multiple horizontal scenarios. In an effect to coherently adapt to various scenarios, and drawing inspiration from the concept of domain-invariant transfer learning, we extend the former SOTA model UniCDR in five different aspects, named as UniCDR+. Our work was successfully deployed on the Kuaishou Living-Room RecSys.