Measure Domain's Gap: A Similar Domain Selection Principle for Multi-Domain Recommendation

2025-05-26

AI Summary

In multi-domain recommendation (MDR), negative transfer problems (NTPs) arise from cross-domain knowledge conflicts and low-quality source domains. To address this, we propose the Similar Domain Selection Principle (SDSP), the first approach to explicitly model domain-level semantic discrepancies: it constructs a lightweight, plug-and-play domain distance metric via prototype learning, jointly leveraging supervised and unsupervised signals; based on this metric, it adaptively selects high-similarity neighboring domains to enable precise knowledge transfer control. Integrated into a multi-domain collaborative recommendation framework, our method achieves significant improvements over state-of-the-art MDR models on three public benchmarks. It effectively mitigates NTPs while incurring negligible inference overhead, demonstrating strong compatibility with existing architectures and practical applicability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Humanities & Computational Social Science
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Multi-Domain Recommendation (MDR) achieves the desirable recommendation performance by effectively utilizing the transfer information across different domains. Despite the great success, most existing MDR methods adopt a single structure to transfer complex domain-shared knowledge. However, the beneficial transferring information should vary across different domains. When there is knowledge conflict between domains or a domain is of poor quality, unselectively leveraging information from all domains will lead to a serious Negative Transfer Problem (NTP). Therefore, how to effectively model the complex transfer relationships between domains to avoid NTP is still a direction worth exploring. To address these issues, we propose a simple and dynamic Similar Domain Selection Principle (SDSP) for multi-domain recommendation in this paper. SDSP presents the initial exploration of selecting suitable domain knowledge for each domain to alleviate NTP. Specifically, we propose a novel prototype-based domain distance measure to effectively model the complexity relationship between domains. Thereafter, the proposed SDSP can dynamically find similar domains for each domain based on the supervised signals of the domain metrics and the unsupervised distance measure from the learned domain prototype. We emphasize that SDSP is a lightweight method that can be incorporated with existing MDR methods for better performance while not introducing excessive time overheads. To the best of our knowledge, it is the first solution that can explicitly measure domain-level gaps and dynamically select appropriate domains in the MDR field. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method.

Problem

• Measure domain gaps to avoid negative transfer in recommendations
• Select similar domains dynamically to enhance knowledge sharing
• Model complex transfer relationships between domains effectively

Innovation

• Dynamic Similar Domain Selection Principle (SDSP)
• Prototype-based domain distance measure
• Lightweight method for multi-domain recommendation