Shallow and Deep Non-IID Learning on Complex Data

Cao, LL; Yu, PS; Zhao, Z

Shallow and Deep Non-IID Learning on Complex Data

Cao, LL Yu, PS Zhao, Z

Permalink

Publisher:: ACM
Publication Type:: Conference Proceeding
Citation:: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2022, pp. 4774-4775
Issue Date:: 2022-08-14

Closed Access

	Filename	Description	Size
	3534678.3542605.pdf	Published version	1.35 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	Cao, LL
dc.contributor.author	Yu, PS
dc.contributor.author	Zhao, Z
dc.date	2022-08-14
dc.date.accessioned	2023-05-15T23:09:02Z
dc.date.available	2023-05-15T23:09:02Z
dc.date.issued	2022-08-14
dc.identifier.citation	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2022, pp. 4774-4775
dc.identifier.isbn	9781450393850
dc.identifier.uri	http://hdl.handle.net/10453/170344
dc.description.abstract	Non-IID (i.i.d.) data holds complex non-IIDness, e.g., couplings and interactions (non-independent) and heterogeneities (not IID drawn from a given distribution). Non-IID learning emerges as a major challenge to shallow and deep learning, including classic statistical learning, mathematical modeling, shallow machine learning, and deep neural learning. Here, we outline the problem, research map, main challenges and topics of shallow and deep non-IID learning.
dc.language	en
dc.publisher	ACM
dc.relation.ispartof	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
dc.relation.ispartof	ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
dc.relation.isbasedon	10.1145/3534678.3542605
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Shallow and Deep Non-IID Learning on Complex Data
dc.type	Conference Proceeding
utslib.location.activity	Washington DC, USA
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	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-05-15T23:09:01Z
pubs.finish-date	2022-08-18
pubs.place-of-publication	USA
pubs.publication-status	Published
pubs.start-date	2022-08-14
dc.location	USA

Abstract:

Non-IID (i.i.d.) data holds complex non-IIDness, e.g., couplings and interactions (non-independent) and heterogeneities (not IID drawn from a given distribution). Non-IID learning emerges as a major challenge to shallow and deep learning, including classic statistical learning, mathematical modeling, shallow machine learning, and deep neural learning. Here, we outline the problem, research map, main challenges and topics of shallow and deep non-IID learning.

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

http://hdl.handle.net/10453/170344