DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (16) · 16853-16861
DOI: 10.1609/aaai.v39i16.33852 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Wenwen Gong und 8 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
Graph Contrastive Learning (GCL), as a primary paradigm of graph self-supervised learning, spurs a fruitful line of research in tackling the data sparsity issue by maximizing the consistency of user/item embeddings between different augmented views with random perturbations. However, diversity, as a crucial metric for recommendation performance and user satisfaction, has received rather little attention. In fact, there exists a challenging dilemma in balancing accuracy and diversity. To address these issues, we propose a new Graph Contrastive Learning (DivGCL) model for diversifying recommendations. Inspired by the excellence of the determinant point process (DPP), DivGCL adopts a DPP likelihood-based loss function to achieve an ideal trade-off between diversity and accuracy, optimizing it jointly with the advanced Gaussian noise-augmented GCL objective. Extensive experiments on four popular datasets demonstrate that DivGCL surpasses existing approaches in balancing accuracy and diversity, with an improvement of 23.47% at T@20 (abbreviation for trade-off metric) on ML-1M.
Zitieren
APA
Gong, W., Geng, Y., Zhang, D., Zhu, Y., Xu, X., Xiang, H., Beheshti, A., Zhang, X., & Qi, L. (2025). DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(16), 16853-16861. https://doi.org/10.1609/aaai.v39i16.33852
Vancouver
Gong W, Geng Y, Zhang D, Zhu Y, Xu X, Xiang H, et al. DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(16):16853-16861. doi:10.1609/aaai.v39i16.33852
BibTeX
@article{Gong2025,
author = {Gong, Wenwen and Geng, Yangliao and Zhang, Dan and Zhu, Yifan and Xu, Xiaolong and Xiang, Haolong and Beheshti, Amin and Zhang, Xuyun and Qi, Lianyong},
title = {DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {16},
pages = {16853--16861},
doi = {10.1609/aaai.v39i16.33852}
}
EUVIMED