模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (6): 479-490    DOI: 10.16451/j.cnki.issn1003-6059.202406001
Multi-prefence and Multi-modality Based Recommender Method Current Issue| Next Issue| Archive| Adv Search |
Multimodal Recommendation Algorithm Based on Contrastive Learning and Semantic Enhancement
ZHANG Kaihan1, FENG Chenjiao2, YAO Kaixuan3, SONG Peng4, LIANG Jiye3
1. School of Computer Science and Technology, North University of China, Taiyuan 030051;
2. School of Applied Mathematics, Shanxi University of Finance and Economics, Taiyuan 030006;
3. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006;
4. School of Economics and Management, Shanxi University, Taiyuan 030031

Download: PDF (1043 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The multimodal data of items is typically introduced into recommendation algorithms as additional auxiliary information to enrich the representation features of users and items. How to effectively integrate the interaction information with multimodal information of users and items is a key issue to the research. Existing methods are still insufficient in feature fusion and semantic association modeling. Therefore, a multimodal recommendation algorithm based on contrastive learning and semantic enhancement is proposed from the perspective of feature fusion. Firstly, the graph neural network and attention mechanism are adopted to fully integrate collaborative features and multimodal features. Next, the semantic association structures within each modality are learned under the guidance of the interaction structure in collaborative information. Meanwhile, the contrastive learning paradigm is employed to capture cross-modal representation dependencies. A reliability factor is introduced into the contrastive loss to adaptively adjust the constraint strength of the multimodal features, consequently suppressing the influence of data noise. Finally, the aforementioned tasks are jointly optimized to generate recommendation results. Experimental results on four real datasets show that the proposed algorithm yields excellent performance.
Key wordsRecommender System      Multimodal Recommendation Algorithm      Graph Neural Network      Contrastive Learning     
Received: 16 March 2024     
ZTFLH: TP 391  
Fund:National Natural Science Foundation of China(No.72171137), Fundamental Research Program of Shanxi Province (No.202203021222075,202203021211331)
Corresponding Authors: LIANG Jiye, Ph.D., professor. His research interests include gra-nular computing, data mining and machine learning.   
About author:: ZHANG Kaihan, Ph.D., lecturer. Her research interests include data mining and recommender system. FENG Chenjiao, Ph.D., associate profe-ssor. Her research interests include data mining and recommender system. YAO Kaixuan, Ph.D., lecturer. His research interests include machine learning and data mining. SONG Peng, Ph.D., professor. His research interests include intelligent decision and data mining.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Kaihan
FENG Chenjiao
YAO Kaixuan
SONG Peng
LIANG Jiye
Cite this article:   
ZHANG Kaihan,FENG Chenjiao,YAO Kaixuan等. Multimodal Recommendation Algorithm Based on Contrastive Learning and Semantic Enhancement[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(6): 479-490.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202406001      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I6/479
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn