Journal article
Collaborative local–global context modeling for session-based recommendation
Information processing & management, Vol.62(5), 104196
09/2025
DOI: 10.1016/j.ipm.2025.104196
Abstract
Session-based recommendation systems (SBRSs) predict the next item in a session by analyzing user interactions. While current methods emphasize sequential item relationships, they often overlook temporal information that highlights subtle shifts in user preferences. This gap can limit their ability to adapt to dynamic user behavior, and recent advances have yet to effectively integrate both sequential and non-sequential item transitions, which may lead to biased modeling. To address these limitations, this paper introduces Coase, a novel SBRS model that unifies local and global context modeling to capture fine-grained dynamic user preferences. Coase transforms session sequences into session star graphs, employing a Bi-Gated Graph Self-Attention Network for local context modeling, and introduces SudokuFormer to model time-aware sequential transitions within a global session context through disentangled attention and stable feature fusion. A triple attention mechanism is then utilized to fully integrate local and global contextual features. Comprehensive experiments conducted on four publicly available datasets demonstrate that Coase improves Recall by 1.71%–1.83%, Mean Reciprocal Rank (MRR) by 2.73%–2.80%, and Normalized Discounted Cumulative Gain (NDCG) by 2.32%–2.43% across the top 5, 10, 15, and 20 items. Ablation studies validate the framework and components of Coase, while additional analyses examine the effect of session length, and visualization studies illustrate diverse attention patterns. This research contributes a novel approach to SBRS, offering promising advancements in recommendation accuracy and user experience.
Details
- Title: Subtitle
- Collaborative local–global context modeling for session-based recommendation
- Creators
- Weiyue Li - Dongbei University of Finance and EconomicsBowei Chen - University of GlasgowMing Gao - Dongbei University of Finance and EconomicsJingmin An - Dongbei University of Finance and EconomicsHao Dong - Dongbei University of Finance and EconomicsCheng Chen - Dongbei University of Finance and EconomicsWeiguo Fan - University of IowaZhiguo Zhu - Dongbei University of Finance and Economics
- Resource Type
- Journal article
- Publication Details
- Information processing & management, Vol.62(5), 104196
- DOI
- 10.1016/j.ipm.2025.104196
- ISSN
- 0306-4573
- eISSN
- 1873-5371
- Publisher
- Elsevier Ltd
- Grant note
- National Natural Science Foundation of China: 72172025, 72293563, 72101051, 72442025 Humanities and Social Sciences Foundation of the Ministry of Education of China: 21YJAZH130 Basic Scientific Research Project of Liaoning Provincial Department of Education: LJKMZ20221606, JYTZD2023050 Natural Science Foundation of Liaoning Province: 2024-MS-175 Liaoning Province Key Research and Development Project: 2024JH2/102400020 Dalian Scientific and Technological Talents Innovation Support Plan: 2022RG17
This research was supported and funded by the National Natural Science Foundation of China (No. 72172025, 72293563, 72101051, 72442025) ; the Humanities and Social Sciences Foundation of the Ministry of Education of China (No. 21YJAZH130) ; the Basic Scientific Research Project of Liaoning Provincial Department of Education (No. LJKMZ20221606, JYTZD2023050) ; the Natural Science Foundation of Liaoning Province (No. 2024-MS-175) ; the Liaoning Province Key Research and Development Project (No. 2024JH2/102400020) ; and the Dalian Scientific and Technological Talents Innovation Support Plan (No. 2022RG17) . The authors would also like to thank Hongyu Wang of the Institute of Computing Technology, Chinese Academy of Sciences, for helpful discussions related to this work.
- Language
- English
- Date published
- 09/2025
- Academic Unit
- Business Analytics
- Record Identifier
- 9984824325702771
Metrics
40 Record Views