Where are we in embedding spaces?

Zhang, S; Chen, H; Ming, X; Cui, L; Yin, H; Xu, G

Where are we in embedding spaces?

Zhang, S Chen, H Ming, X Cui, L Yin, H Xu, G

Permalink

Publisher:: ACM
Publication Type:: Conference Proceeding
Citation:: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2021, pp. 2223-2231
Issue Date:: 2021-08-14

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (2.06 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, S
dc.contributor.author	Chen, H
dc.contributor.author	Ming, X
dc.contributor.author	Cui, L
dc.contributor.author	Yin, H
dc.contributor.author	Xu, G https://orcid.org/0000-0003-4493-6663
dc.date.accessioned	2022-01-19T00:05:30Z
dc.date.available	2022-01-19T00:05:30Z
dc.date.issued	2021-08-14
dc.identifier.citation	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2021, pp. 2223-2231
dc.identifier.isbn	9781450383325
dc.identifier.uri	http://hdl.handle.net/10453/153314
dc.description.abstract	Hyperbolic space and hyperbolic embeddings are becoming a popular research field for recommender systems. However, it is not clear under what circumstances the hyperbolic space should be considered. To fill this gap, This paper provides theoretical analysis and empirical results on when and where to use hyperbolic space and hyperbolic embeddings in recommender systems. Specifically, we answer the questions that which type of models and datasets are more suited for hyperbolic space, as well as which latent size to choose. We evaluate our answers by comparing the performance of Euclidean space and hyperbolic space on different latent space models in both general item recommendation domain and social recommendation domain, with 6 widely used datasets and different latent sizes. Additionally, we propose a new metric learning based recommendation method called SCML and its hyperbolic version HSCML. We evaluate our conclusions regarding hyperbolic space on SCML and show the state-of-the-art performance of hyperbolic space by comparing HSCML with other baseline methods.
dc.language	en
dc.publisher	ACM
dc.relation	http://purl.org/au-research/grants/arc/LP170100891
dc.relation	http://purl.org/au-research/grants/arc/DP200101374
dc.relation.ispartof	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
dc.relation.ispartof	KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
dc.relation.isbasedon	10.1145/3447548.3467421
dc.rights	© ACM 2021. 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 Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Pagination 2223-2231 Publication date 14 Aug 2021 https://dl.acm.org/doi/abs/10.1145/2892208.2892235
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Where are we in embedding spaces?
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	2022-01-19T00:05:29Z
pubs.publication-status	Published

Abstract:

Hyperbolic space and hyperbolic embeddings are becoming a popular research field for recommender systems. However, it is not clear under what circumstances the hyperbolic space should be considered. To fill this gap, This paper provides theoretical analysis and empirical results on when and where to use hyperbolic space and hyperbolic embeddings in recommender systems. Specifically, we answer the questions that which type of models and datasets are more suited for hyperbolic space, as well as which latent size to choose. We evaluate our answers by comparing the performance of Euclidean space and hyperbolic space on different latent space models in both general item recommendation domain and social recommendation domain, with 6 widely used datasets and different latent sizes. Additionally, we propose a new metric learning based recommendation method called SCML and its hyperbolic version HSCML. We evaluate our conclusions regarding hyperbolic space on SCML and show the state-of-the-art performance of hyperbolic space by comparing HSCML with other baseline methods.

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

http://hdl.handle.net/10453/153314