MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation
Abstract Graph Convolutional Networks (GCNs) have achieved remarkable success in recommendation systems by leveraging higher-order neighborhoods. In recent years, multi-behavior recommendation has addressed the challenges of data sparsity and cold start problems to some extent. However, the introduc...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-04-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-025-01880-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850272803201220608 |
|---|---|
| author | Xiaowen lv Yiwei Zhao Zhihu Zhou Yifeng Zhang Yourong Chen |
| author_facet | Xiaowen lv Yiwei Zhao Zhihu Zhou Yifeng Zhang Yourong Chen |
| author_sort | Xiaowen lv |
| collection | DOAJ |
| description | Abstract Graph Convolutional Networks (GCNs) have achieved remarkable success in recommendation systems by leveraging higher-order neighborhoods. In recent years, multi-behavior recommendation has addressed the challenges of data sparsity and cold start problems to some extent. However, the introduction of noise from multi-behavior tasks into the user-item graph exacerbates the impact of noise from a few active users and popularity bias from popular items. To tackle these challenges, graph augmentation has emerged as a promising approach in recommendation systems. However, existing augmentation methods may generate suboptimal graph structures, and maximizing correspondence may capture information unrelated to the recommendation task. To address these issues, we propose a novel approach called the Multi-Behavior Adaptive Graph Contrastive Learning Model (MB-AGCL) for recommendation. Our approach integrates auxiliary behaviors to compensate for data sparsity and utilizes adaptive learning to determine whether to drop edges or nodes, thus obtaining an optimized graph structure that reduces the impact of noise. We then train the original and generated graphs using supervised tasks. Furthermore, we propose an efficient adaptive graph augmentation method that integrates graph augmentation with down-stream tasks to reduce the impact of popularity bias. Finally, we jointly optimize these two tasks. Through extensive experiments on public datasets, we validate the effectiveness of our recommendation model. |
| format | Article |
| id | doaj-art-fa11ea5dacae4ec9839478326500d0ae |
| institution | OA Journals |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-fa11ea5dacae4ec9839478326500d0ae2025-08-20T01:51:41ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-04-0111611210.1007/s40747-025-01880-2MB-AGCL: multi-behavior adaptive graph contrast learning for recommendationXiaowen lv0Yiwei Zhao1Zhihu Zhou2Yifeng Zhang3Yourong Chen4College of Information Science and Technology, Zhejiang Shuren UniversityCollege of Information Science and Technology, Zhejiang Shuren UniversityCollege of Information Engineering, Zhejiang University of TechnologyTsinghua UniversityCollege of Information Science and Technology, Zhejiang Shuren UniversityAbstract Graph Convolutional Networks (GCNs) have achieved remarkable success in recommendation systems by leveraging higher-order neighborhoods. In recent years, multi-behavior recommendation has addressed the challenges of data sparsity and cold start problems to some extent. However, the introduction of noise from multi-behavior tasks into the user-item graph exacerbates the impact of noise from a few active users and popularity bias from popular items. To tackle these challenges, graph augmentation has emerged as a promising approach in recommendation systems. However, existing augmentation methods may generate suboptimal graph structures, and maximizing correspondence may capture information unrelated to the recommendation task. To address these issues, we propose a novel approach called the Multi-Behavior Adaptive Graph Contrastive Learning Model (MB-AGCL) for recommendation. Our approach integrates auxiliary behaviors to compensate for data sparsity and utilizes adaptive learning to determine whether to drop edges or nodes, thus obtaining an optimized graph structure that reduces the impact of noise. We then train the original and generated graphs using supervised tasks. Furthermore, we propose an efficient adaptive graph augmentation method that integrates graph augmentation with down-stream tasks to reduce the impact of popularity bias. Finally, we jointly optimize these two tasks. Through extensive experiments on public datasets, we validate the effectiveness of our recommendation model.https://doi.org/10.1007/s40747-025-01880-2RecommendationContrastive learningGraph representationSelf-supervised learning |
| spellingShingle | Xiaowen lv Yiwei Zhao Zhihu Zhou Yifeng Zhang Yourong Chen MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation Complex & Intelligent Systems Recommendation Contrastive learning Graph representation Self-supervised learning |
| title | MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation |
| title_full | MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation |
| title_fullStr | MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation |
| title_full_unstemmed | MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation |
| title_short | MB-AGCL: multi-behavior adaptive graph contrast learning for recommendation |
| title_sort | mb agcl multi behavior adaptive graph contrast learning for recommendation |
| topic | Recommendation Contrastive learning Graph representation Self-supervised learning |
| url | https://doi.org/10.1007/s40747-025-01880-2 |
| work_keys_str_mv | AT xiaowenlv mbagclmultibehavioradaptivegraphcontrastlearningforrecommendation AT yiweizhao mbagclmultibehavioradaptivegraphcontrastlearningforrecommendation AT zhihuzhou mbagclmultibehavioradaptivegraphcontrastlearningforrecommendation AT yifengzhang mbagclmultibehavioradaptivegraphcontrastlearningforrecommendation AT yourongchen mbagclmultibehavioradaptivegraphcontrastlearningforrecommendation |