Deep heterogeneous autoencoders for Collaborative Filtering

This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems. We propose a model that learns a shared feature space from heterogeneous data, such as item descriptions, product tags and online purchase history, to obtain better predictions. Our...

Full description

Saved in:

Bibliographic Details
Main Authors:	Li, Tianyu, Ma, Yukun, Xu, Jiu, Stenger, Björn, Liu, Chen, Hirate, Yu
Other Authors:	School of Computer Science and Engineering
Format:	Conference or Workshop Item
Language:	English
Published:	2020
Subjects:	Engineering::Computer science and engineering Deep Autoencoder Heterogeneous Data
Online Access:	https://hdl.handle.net/10356/144026
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-144026
record_format	dspace
spelling	sg-ntu-dr.10356-1440262020-10-08T06:50:04Z Deep heterogeneous autoencoders for Collaborative Filtering Li, Tianyu Ma, Yukun Xu, Jiu Stenger, Björn Liu, Chen Hirate, Yu School of Computer Science and Engineering 2018 IEEE International Conference on Data Mining (ICDM) Centre for Computational Intelligence Engineering::Computer science and engineering Deep Autoencoder Heterogeneous Data This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems. We propose a model that learns a shared feature space from heterogeneous data, such as item descriptions, product tags and online purchase history, to obtain better predictions. Our model consists of autoencoders, not only for numerical and categorical data, but also for sequential data, which enables capturing user tastes, item characteristics and the recent dynamics of user preference. We learn the autoencoder architecture for each data source independently in order to better model their statistical properties. Our evaluation on two MovieLens datasets and an e-commerce dataset shows that mean average precision and recall improve over state-of-the-art methods. Accepted version 2020-10-08T06:50:04Z 2020-10-08T06:50:04Z 2018 Conference Paper Li, T., Ma, Y., Xu, J., Stenger, B., Liu, C., & Hirate, Y. (2018). Deep heterogeneous autoencoders for Collaborative Filtering. Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), 1164-1169. doi:10.1109/icdm.2018.00153 978-1-5386-9160-1 https://hdl.handle.net/10356/144026 10.1109/ICDM.2018.00153 1164 1169 en © 2018 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. The published version is available at: https://doi.org/10.1109/ICDM.2018.00153 application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	Engineering::Computer science and engineering Deep Autoencoder Heterogeneous Data
spellingShingle	Engineering::Computer science and engineering Deep Autoencoder Heterogeneous Data Li, Tianyu Ma, Yukun Xu, Jiu Stenger, Björn Liu, Chen Hirate, Yu Deep heterogeneous autoencoders for Collaborative Filtering
description	This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems. We propose a model that learns a shared feature space from heterogeneous data, such as item descriptions, product tags and online purchase history, to obtain better predictions. Our model consists of autoencoders, not only for numerical and categorical data, but also for sequential data, which enables capturing user tastes, item characteristics and the recent dynamics of user preference. We learn the autoencoder architecture for each data source independently in order to better model their statistical properties. Our evaluation on two MovieLens datasets and an e-commerce dataset shows that mean average precision and recall improve over state-of-the-art methods.
author2	School of Computer Science and Engineering
author_facet	School of Computer Science and Engineering Li, Tianyu Ma, Yukun Xu, Jiu Stenger, Björn Liu, Chen Hirate, Yu
format	Conference or Workshop Item
author	Li, Tianyu Ma, Yukun Xu, Jiu Stenger, Björn Liu, Chen Hirate, Yu
author_sort	Li, Tianyu
title	Deep heterogeneous autoencoders for Collaborative Filtering
title_short	Deep heterogeneous autoencoders for Collaborative Filtering
title_full	Deep heterogeneous autoencoders for Collaborative Filtering
title_fullStr	Deep heterogeneous autoencoders for Collaborative Filtering
title_full_unstemmed	Deep heterogeneous autoencoders for Collaborative Filtering
title_sort	deep heterogeneous autoencoders for collaborative filtering
publishDate	2020
url	https://hdl.handle.net/10356/144026
_version_	1681059285953413120

Deep heterogeneous autoencoders for Collaborative Filtering

Similar Items