Music recommendation via heterogeneous information graph embedding

Wang, D; Xu, G; Deng, S

Music recommendation via heterogeneous information graph embedding

Wang, D Xu, G

Deng, S

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the International Joint Conference on Neural Networks, 2017, 2017-May pp. 596 - 603
Issue Date:: 2017-06-30

In Progress

	Filename	Description	Size
	07965907 (002).pdf	Accepted Manuscript	382.61 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is being processed and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, D	en_US
dc.contributor.author	Xu, G https://orcid.org/0000-0003-4493-6663	en_US
dc.contributor.author	Deng, S	en_US
dc.date.issued	2017-06-30	en_US
dc.identifier.citation	Proceedings of the International Joint Conference on Neural Networks, 2017, 2017-May pp. 596 - 603	en_US
dc.identifier.isbn	9781509061815	en_US
dc.identifier.uri	http://hdl.handle.net/10453/111107
dc.description.abstract	© 2017 IEEE. Traditional music recommendation techniques suffer from limited performance due to the sparsity of user-music interaction data, which is addressed by incorporating auxiliary information. In this paper, we study the problem of personalized music recommendation that takes different kinds of auxiliary information into consideration. To achieve this goal, a Heterogeneous Information Graph (HIG) is first constructed to encode different kinds of heterogeneous information, including the interactions between users and music pieces, music playing sequences, and the metadata of music pieces. Based on HIG, a Heterogeneous Information Graph Embedding method (HIGE) is proposed to learn the latent low-dimensional representations of music pieces. Then, we further develop a context-aware music recommendation method. Extensive experiments have been conducted on real-world datasets to compare the proposed method with other state-of-the-art recommendation methods. The results demonstrate that the proposed method significantly outperforms those baselines, especially on sparse datasets.	en_US
dc.relation.ispartof	Proceedings of the International Joint Conference on Neural Networks	en_US
dc.relation.isbasedon	10.1109/IJCNN.2017.7965907	en_US
dc.title	Music recommendation via heterogeneous information graph embedding	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2017-May	en_US
utslib.for	080105 Expert Systems	en_US
pubs.embargo.period	Not known	en_US
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
pubs.organisational-group	/University of Technology Sydney/Strength - AAI - Advanced Analytics Institute Research Centre
utslib.copyright.status	in_progress
pubs.publication-status	Published	en_US
pubs.volume	2017-May	en_US

Abstract:

© 2017 IEEE. Traditional music recommendation techniques suffer from limited performance due to the sparsity of user-music interaction data, which is addressed by incorporating auxiliary information. In this paper, we study the problem of personalized music recommendation that takes different kinds of auxiliary information into consideration. To achieve this goal, a Heterogeneous Information Graph (HIG) is first constructed to encode different kinds of heterogeneous information, including the interactions between users and music pieces, music playing sequences, and the metadata of music pieces. Based on HIG, a Heterogeneous Information Graph Embedding method (HIGE) is proposed to learn the latent low-dimensional representations of music pieces. Then, we further develop a context-aware music recommendation method. Extensive experiments have been conducted on real-world datasets to compare the proposed method with other state-of-the-art recommendation methods. The results demonstrate that the proposed method significantly outperforms those baselines, especially on sparse datasets.

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

http://hdl.handle.net/10453/111107