Knowledge graph self-supervised contrastive learning for recommendation

Shuhan Wang; Yan Jiang; Liang Chen; Jiaze Lu

doi:10.1117/12.3031121

19 July 2024 Knowledge graph self-supervised contrastive learning for recommendation

Shuhan Wang, Yan Jiang, Liang Chen, Jiaze Lu

Author Affiliations +

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 1318189 (2024) https://doi.org/10.1117/12.3031121
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

Knowledge graphs play a central role in the field of recommender systems, and their quality directly impacts their performance in deep applications. Real-world knowledge graphs are often subject to noise, which disrupts the precise representation of user preferences. This paper proposes a Knowledge Graph-based Contrastive Learning framework, KGRSL, aiming to enhance perceptual capabilities through an augmented knowledge graph. Simultaneously, we employ self-supervised signals to lead the contrastive learning example, further restrain noise. The proposed model demonstrates effectiveness, as evidenced by improved recall rates and NDCG scores across three public datasets—Last.FM, MIND, and Yelp2018. The results indicate that our proposed framework KGRSL has shown improvements of 3.47%, 6.22%, and 11.02% in Recall@20 compared to recent baseline models.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shuhan Wang, Yan Jiang, Liang Chen, and Jiaze Lu "Knowledge graph self-supervised contrastive learning for recommendation", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 1318189 (19 July 2024); https://doi.org/10.1117/12.3031121

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE