Geometric inductive matrix completion: A hyperbolic approach with unified message passing

Zhang, C; Chen, H; Zhang, S; Xu, G; Gao, J

Geometric inductive matrix completion: A hyperbolic approach with unified message passing

Zhang, C Chen, H Zhang, S Xu, G

Gao, J

Permalink

Publisher:: ACM
Publication Type:: Conference Proceeding
Citation:: WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining, 2022, pp. 1337-1346
Issue Date:: 2022-02-11

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (1.72 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, C
dc.contributor.author	Chen, H
dc.contributor.author	Zhang, S
dc.contributor.author	Xu, G https://orcid.org/0000-0003-4493-6663
dc.contributor.author	Gao, J
dc.date.accessioned	2022-04-11T06:37:56Z
dc.date.available	2022-04-11T06:37:56Z
dc.date.issued	2022-02-11
dc.identifier.citation	WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining, 2022, pp. 1337-1346
dc.identifier.isbn	9781450391320
dc.identifier.uri	http://hdl.handle.net/10453/156070
dc.description.abstract	Collaborative filtering is a central task in a broad range of recommender systems. As traditional methods train latent variables for user/item individuals under a transductive setting, it requires re-training for out-of-sample inferences. Inductive matrix completion (IMC) solves this problem by learning transformation functions upon engineered features, but it sacrifices model expressiveness and highly depends on feature qualities. In this paper, we propose Geometric Inductive Matrix Completion (GIMC) by introducing hyperbolic geometry and a unified message passing scheme into this generic task. The proposed method is the earliest attempt utilizing capacious hyperbolic space to enhance the capacity of IMC. It is the first work defining continuous explicit feedback prediction within non-Euclidean space by introducing hyperbolic regression for vertex interactions. This is also the first to provide comprehensive evidence that edge semantics can significantly improve recommendations, which is ignored by previous works. The proposed method outperforms the state-of-the-art algorithms with less than 1% parameters compared to its transductive counterparts. Extensive analysis and ablation studies are conducted to reveal the design considerations and practicability for a positive impact to the research community.
dc.language	en
dc.publisher	ACM
dc.relation	http://purl.org/au-research/grants/arc/DP200101374
dc.relation.ispartof	WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining
dc.relation.ispartof	Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
dc.relation.isbasedon	10.1145/3488560.3498402
dc.rights	© ACM 2022. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining Pagination 1337 - 1346 Publication date 11 Feb 2022 https://dl.acm.org/doi/10.1145/3488560.3498402
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Geometric inductive matrix completion: A hyperbolic approach with unified message passing
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/Strength - AAI - Advanced Analytics Institute Research Centre
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
dc.date.updated	2022-04-11T06:37:54Z
pubs.publication-status	Published

Abstract:

Collaborative filtering is a central task in a broad range of recommender systems. As traditional methods train latent variables for user/item individuals under a transductive setting, it requires re-training for out-of-sample inferences. Inductive matrix completion (IMC) solves this problem by learning transformation functions upon engineered features, but it sacrifices model expressiveness and highly depends on feature qualities. In this paper, we propose Geometric Inductive Matrix Completion (GIMC) by introducing hyperbolic geometry and a unified message passing scheme into this generic task. The proposed method is the earliest attempt utilizing capacious hyperbolic space to enhance the capacity of IMC. It is the first work defining continuous explicit feedback prediction within non-Euclidean space by introducing hyperbolic regression for vertex interactions. This is also the first to provide comprehensive evidence that edge semantics can significantly improve recommendations, which is ignored by previous works. The proposed method outperforms the state-of-the-art algorithms with less than 1% parameters compared to its transductive counterparts. Extensive analysis and ablation studies are conducted to reveal the design considerations and practicability for a positive impact to the research community.

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

http://hdl.handle.net/10453/156070