Mix2Vec: Unsupervised mixed data representation

Zhu, C; Zhang, Q; Cao, L; Abrahamyan, A

Mix2Vec: Unsupervised mixed data representation

Zhu, C Zhang, Q Cao, L

Abrahamyan, A

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - 2020 IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020, 2020, 00, pp. 118-127
Issue Date:: 2020-10-01

Closed Access

	Filename	Description	Size
	dsaa2020-final.pdf	Accepted version	970.49 kB	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	Zhu, C
dc.contributor.author	Zhang, Q
dc.contributor.author	Cao, L https://orcid.org/0000-0003-1562-9429
dc.contributor.author	Abrahamyan, A
dc.date	2020-10-06
dc.date.accessioned	2021-04-01T11:09:55Z
dc.date.available	2021-04-01T11:09:55Z
dc.date.issued	2020-10-01
dc.identifier.citation	Proceedings - 2020 IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020, 2020, 00, pp. 118-127
dc.identifier.isbn	9781728182063
dc.identifier.uri	http://hdl.handle.net/10453/147804
dc.description.abstract	Unsupervised representation learning on mixed data is highly challenging but rarely explored. It has to tackle significant challenges related to common issues in real-life mixed data, including sparsity, dynamics and heterogeneity of attributes and values. This work introduces an effective and efficient unsupervised deep representer called Mix2Vec to automatically learn a universal representation of dynamic mixed data with the above complex characteristics. Mix2Vec is empowered with three effective mechanisms: random shuffling prediction, prior distribution matching, and structural informativeness maximization, to tackle the aforementioned challenges. These mechanisms are implemented as an unsupervised deep neural representer Mix2Vec. Mix2Vec converts complex mixed data into vector space-based representations that are universal and comparable to all data objects and transparent and reusable for both unsupervised and supervised learning tasks. Extensive experiments on four large mixed datasets demonstrate that Mix2Vec performs significantly better than state-of-the-art deep representation methods. We also empirically verify the designed mechanisms in terms of representation quality, visualization and capability of enabling better performance of downstream tasks.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - 2020 IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020
dc.relation.ispartof	2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA)
dc.relation.isbasedon	10.1109/DSAA49011.2020.00024
dc.rights	info:eu-repo/semantics/closedAccess
dc.rights	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.title	Mix2Vec: Unsupervised mixed data representation
dc.type	Conference Proceeding
utslib.citation.volume	00
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/A/DRsch The Data Science Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2021-04-01T11:09:54Z
pubs.finish-date	2020-10-09
pubs.publication-status	Published
pubs.start-date	2020-10-06
pubs.volume	00

Abstract:

Unsupervised representation learning on mixed data is highly challenging but rarely explored. It has to tackle significant challenges related to common issues in real-life mixed data, including sparsity, dynamics and heterogeneity of attributes and values. This work introduces an effective and efficient unsupervised deep representer called Mix2Vec to automatically learn a universal representation of dynamic mixed data with the above complex characteristics. Mix2Vec is empowered with three effective mechanisms: random shuffling prediction, prior distribution matching, and structural informativeness maximization, to tackle the aforementioned challenges. These mechanisms are implemented as an unsupervised deep neural representer Mix2Vec. Mix2Vec converts complex mixed data into vector space-based representations that are universal and comparable to all data objects and transparent and reusable for both unsupervised and supervised learning tasks. Extensive experiments on four large mixed datasets demonstrate that Mix2Vec performs significantly better than state-of-the-art deep representation methods. We also empirically verify the designed mechanisms in terms of representation quality, visualization and capability of enabling better performance of downstream tasks.

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

http://hdl.handle.net/10453/147804