Deep Learning for Approximate Nearest Neighbour Search: A Survey and Future Directions

Li, M; Wang, YG; Zhang, P; Wang, H; Fan, L; Li, E; Wang, W

Deep Learning for Approximate Nearest Neighbour Search: A Survey and Future Directions

Li, M

Wang, YG Zhang, P Wang, H Fan, L Li, E Wang, W

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Transactions on Knowledge and Data Engineering, 2022, PP, (99), pp. 1-20
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Deep Learning for Approximate Nearest Neighbour Search A Survey and Future Directions.pdf	Published version	1.97 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, M https://orcid.org/0000-0003-3565-1180
dc.contributor.author	Wang, YG
dc.contributor.author	Zhang, P
dc.contributor.author	Wang, H
dc.contributor.author	Fan, L
dc.contributor.author	Li, E
dc.contributor.author	Wang, W
dc.date.accessioned	2023-03-21T04:41:27Z
dc.date.available	2023-03-21T04:41:27Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Knowledge and Data Engineering, 2022, PP, (99), pp. 1-20
dc.identifier.issn	1041-4347
dc.identifier.issn	1558-2191
dc.identifier.uri	http://hdl.handle.net/10453/167948
dc.description.abstract	Approximate nearest neighbour search (ANNS) in high-dimensional space is an essential and fundamental operation in many applications from many domains such as multimedia database, information retrieval and computer vision. With the rapidly growing volume of data and the dramatically increasing demands of users, traditional heuristic-based ANNS solutions have been facing great challenges in terms of both efficiency and accuracy. Inspired by the recent successes of deep learning in many fields, substantial efforts have been devoted to applying deep learning techniques to ANNS for learning to index and learning to search, resulting in numerous algorithms that achieve state-of-the-art performance compared with conventional methods. In this survey paper, we comprehensively review the different types of deep learning-based ANNS methods according to two learning paradigms: <italic>learning to index</italic> and <italic>learning to search</italic>. We provide a comprehensive overview and analysis of these methods in a systematic manner. Based on the overview, we point out that <italic>end-to-end learning</italic> will be a new and promising research direction for deep learning-based ANNS, i.e., applying deep learning techniques to jointly learn the indexing and searching together, such that the underlying knowledge learned from data can directly contribute to the final searching performance. Finally, we conduct experiments and provide general performance analyses for the representative deep learning-based ANNS algorithms.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Transactions on Knowledge and Data Engineering
dc.relation.isbasedon	10.1109/TKDE.2022.3220683
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences
dc.subject.classification	Information Systems
dc.title	Deep Learning for Approximate Nearest Neighbour Search: A Survey and Future Directions
dc.type	Journal Article
utslib.citation.volume	PP
utslib.for	08 Information and Computing Sciences
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/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-21T04:41:26Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Approximate nearest neighbour search (ANNS) in high-dimensional space is an essential and fundamental operation in many applications from many domains such as multimedia database, information retrieval and computer vision. With the rapidly growing volume of data and the dramatically increasing demands of users, traditional heuristic-based ANNS solutions have been facing great challenges in terms of both efficiency and accuracy. Inspired by the recent successes of deep learning in many fields, substantial efforts have been devoted to applying deep learning techniques to ANNS for learning to index and learning to search, resulting in numerous algorithms that achieve state-of-the-art performance compared with conventional methods. In this survey paper, we comprehensively review the different types of deep learning-based ANNS methods according to two learning paradigms: learning to index and learning to search. We provide a comprehensive overview and analysis of these methods in a systematic manner. Based on the overview, we point out that end-to-end learning will be a new and promising research direction for deep learning-based ANNS, i.e., applying deep learning techniques to jointly learn the indexing and searching together, such that the underlying knowledge learned from data can directly contribute to the final searching performance. Finally, we conduct experiments and provide general performance analyses for the representative deep learning-based ANNS algorithms.

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

http://hdl.handle.net/10453/167948