Multi-Domain Sequential Recommendation via Domain Space Learning
Open Access
- 10 July 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2134-2144
Abstract
This paper explores Multi-Domain Sequential Recommendation (MDSR), an advancement of Multi-Domain Recommendation that incorporates sequential context. Recent MDSR approach exploits domain-specific sequences, decoupled from mixed-domain histories, to model domain-specific sequential preference, and use mixeddomain histories to model domain-shared sequential preference. However, the approach faces challenges in accurately obtaining domain-specific sequential preferences in the target domain, especially when users only occasionally engage with it. In such cases, the history of users in the target domain is limited or not recent, leading the sequential recommender system to capture inaccurate domain-specific sequential preferences. To address this limitation, this paper introduces Multi-Domain Sequential Recommendation via Domain Space Learning (MDSR-DSL). Our approach utilizes cross-domain items to supplement missing sequential context in domain-specific sequences. It involves creating a "domain space" to maintain and utilize the unique characteristics of each domain and a domain-to-domain adaptation mechanism to transform item representations across domain spaces. To validate the effectiveness of MDSR-DSL, this paper extensively compares it with state-of-the-art MD(S)R methods and provides detailed analyses.Keywords
Funding Information
- National Research Foundation of Korea (RS-2023-00217286)
- Institute for Information and Communications Technology Promotion (2018-0-00584,2019-0-01906)
- Daegu Digital Innovation Promotion Agency (DBSD1-07)
This publication has 41 references indexed in Scilit:
- Decoupled Knowledge Distillation2022
- Contrastive Learning for Sequential Recommendation2022
- DE-RRD: A Knowledge Distillation Framework for Recommender System2020
- Online Knowledge Distillation via Collaborative Learning2020
- DDTCDR2020
- Hierarchical Gating Networks for Sequential Recommendation2019
- Neural Graph Collaborative Filtering2019
- Deep Mutual Learning2018
- Ups and Downs2016
- Relational learning via collective matrix factorization2008