SGCCL: Siamese Graph Contrastive Consensus Learning for Personalized Recommendation

Li, B; Guo, T; Zhu, X; Li, Q; Wang, Y; Chen, F

SGCCL: Siamese Graph Contrastive Consensus Learning for Personalized Recommendation

Li, B Guo, T

Zhu, X Li, Q Wang, Y

Chen, F

Permalink

Publisher:: Association for Computing Machinery (ACM)
Publication Type:: Conference Proceeding
Citation:: WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining, 2023, pp. 589-597
Issue Date:: 2023-02-27

In Progress

	Filename	Description	Size
	SGCCL_2023.pdf	Published version	470.01 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is being processed and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, B
dc.contributor.author	Guo, T https://orcid.org/0000-0001-5130-3237
dc.contributor.author	Zhu, X
dc.contributor.author	Li, Q
dc.contributor.author	Wang, Y https://orcid.org/0000-0002-6815-0879
dc.contributor.author	Chen, F https://orcid.org/0000-0003-4971-8729
dc.date.accessioned	2024-02-28T05:03:47Z
dc.date.available	2024-02-28T05:03:47Z
dc.date.issued	2023-02-27
dc.identifier.citation	WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining, 2023, pp. 589-597
dc.identifier.isbn	9781450394079
dc.identifier.uri	http://hdl.handle.net/10453/175923
dc.description.abstract	Contrastive-learning-based neural networks have recently been introduced to recommender systems, due to their unique advantage of injecting collaborative signals to model deep representations, and the self-supervision nature in the learning process. Existing contrastive learning methods for recommendations are mainly proposed through introducing augmentations to the user-item (U-I) bipartite graphs. Such a contrastive learning process, however, is susceptible to bias towards popular items and users, because higher-degree users/items are subject to more augmentations and their correlations are more captured. In this paper, we advocate a Siamese Graph Contrastive Consensus Learning (SGCCL) framework, to explore intrinsic correlations and alleviate the bias effects for personalized recommendation. Instead of augmenting original U-I networks, we introduce siamese graphs, which are homogeneous relations of user-user (U-U) similarity and item-item (I-I) correlations. A contrastive consensus optimization process is also adopted to learn effective features for user-item ratings, user-user similarity, and item-item correlation. Finally, we employ the self-supervised learning coupled with the siamese item-item/user-user graph relationships, which ensures unpopular users/items are well preserved in the embedding space. Different from existing studies, SGCCL performs well on both overall and debiasing recommendation tasks resulting in a balanced recommender. Experiments on four benchmark datasets demonstrate that SGCCL outperforms state-of-the-art methods with higher accuracy and greater long-tail item/user exposure.
dc.language	en
dc.publisher	Association for Computing Machinery (ACM)
dc.relation.ispartof	WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining
dc.relation.ispartof	Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining
dc.relation.isbasedon	10.1145/3539597.3570422
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	SGCCL: Siamese Graph Contrastive Consensus Learning for Personalized Recommendation
dc.type	Conference Proceeding
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
utslib.copyright.status	in_progress	*
dc.date.updated	2024-02-28T05:03:45Z
pubs.publication-status	Published

Abstract:

Contrastive-learning-based neural networks have recently been introduced to recommender systems, due to their unique advantage of injecting collaborative signals to model deep representations, and the self-supervision nature in the learning process. Existing contrastive learning methods for recommendations are mainly proposed through introducing augmentations to the user-item (U-I) bipartite graphs. Such a contrastive learning process, however, is susceptible to bias towards popular items and users, because higher-degree users/items are subject to more augmentations and their correlations are more captured. In this paper, we advocate a Siamese Graph Contrastive Consensus Learning (SGCCL) framework, to explore intrinsic correlations and alleviate the bias effects for personalized recommendation. Instead of augmenting original U-I networks, we introduce siamese graphs, which are homogeneous relations of user-user (U-U) similarity and item-item (I-I) correlations. A contrastive consensus optimization process is also adopted to learn effective features for user-item ratings, user-user similarity, and item-item correlation. Finally, we employ the self-supervised learning coupled with the siamese item-item/user-user graph relationships, which ensures unpopular users/items are well preserved in the embedding space. Different from existing studies, SGCCL performs well on both overall and debiasing recommendation tasks resulting in a balanced recommender. Experiments on four benchmark datasets demonstrate that SGCCL outperforms state-of-the-art methods with higher accuracy and greater long-tail item/user exposure.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/175923