IEICE TRANSACTIONS on Information
Hierarchical Preference Hash Network for News Recommendation
Summary :
Personalized news recommendation is becoming increasingly important for online news platforms to help users alleviate information overload and improve news reading experience. A key problem in news recommendation is learning accurate user representations to capture their interest. However, most existing news recommendation methods usually learn user representation only from their interacted historical news, while ignoring the clustering features among users. Here we proposed a hierarchical user preference hash network to enhance the representation of users' interest. In the hash part, a series of buckets are generated based on users' historical interactions. Users with similar preferences are assigned into the same buckets automatically. We also learn representations of users from their browsed news in history part. And then, a Route Attention is adopted to combine these two parts (history vector and hash vector) and get the more informative user preference vector. As for news representation, a modified transformer with category embedding is exploited to build news semantic representation. By comparing the hierarchical hash network with multiple news recommendation methods and conducting various experiments on the Microsoft News Dataset (MIND) validate the effectiveness of our approach on news recommendation.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.2 pp.355-363
- Publication Date
- 2022/02/01
- Publicized
- 2021/10/22
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021EDP7034
- Type of Manuscript
- PAPER
- Category
- Artificial Intelligence, Data Mining
Authors
Jianyong DUAN
North China University of Technology,CNONIX National Standard Application and Promotion Lab
Liangcai LI
North China University of Technology,CNONIX National Standard Application and Promotion Lab
Mei ZHANG
North China University of Technology
Hao WANG
North China University of Technology,CNONIX National Standard Application and Promotion Lab
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jianyong DUAN, Liangcai LI, Mei ZHANG, Hao WANG, "Hierarchical Preference Hash Network for News Recommendation" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 2, pp. 355-363, February 2022, doi: 10.1587/transinf.2021EDP7034.
Abstract: Personalized news recommendation is becoming increasingly important for online news platforms to help users alleviate information overload and improve news reading experience. A key problem in news recommendation is learning accurate user representations to capture their interest. However, most existing news recommendation methods usually learn user representation only from their interacted historical news, while ignoring the clustering features among users. Here we proposed a hierarchical user preference hash network to enhance the representation of users' interest. In the hash part, a series of buckets are generated based on users' historical interactions. Users with similar preferences are assigned into the same buckets automatically. We also learn representations of users from their browsed news in history part. And then, a Route Attention is adopted to combine these two parts (history vector and hash vector) and get the more informative user preference vector. As for news representation, a modified transformer with category embedding is exploited to build news semantic representation. By comparing the hierarchical hash network with multiple news recommendation methods and conducting various experiments on the Microsoft News Dataset (MIND) validate the effectiveness of our approach on news recommendation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7034/_p
Copy
@ARTICLE{e105-d_2_355,
author={Jianyong DUAN, Liangcai LI, Mei ZHANG, Hao WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Hierarchical Preference Hash Network for News Recommendation},
year={2022},
volume={E105-D},
number={2},
pages={355-363},
abstract={Personalized news recommendation is becoming increasingly important for online news platforms to help users alleviate information overload and improve news reading experience. A key problem in news recommendation is learning accurate user representations to capture their interest. However, most existing news recommendation methods usually learn user representation only from their interacted historical news, while ignoring the clustering features among users. Here we proposed a hierarchical user preference hash network to enhance the representation of users' interest. In the hash part, a series of buckets are generated based on users' historical interactions. Users with similar preferences are assigned into the same buckets automatically. We also learn representations of users from their browsed news in history part. And then, a Route Attention is adopted to combine these two parts (history vector and hash vector) and get the more informative user preference vector. As for news representation, a modified transformer with category embedding is exploited to build news semantic representation. By comparing the hierarchical hash network with multiple news recommendation methods and conducting various experiments on the Microsoft News Dataset (MIND) validate the effectiveness of our approach on news recommendation.},
keywords={},
doi={10.1587/transinf.2021EDP7034},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Hierarchical Preference Hash Network for News Recommendation
T2 - IEICE TRANSACTIONS on Information
SP - 355
EP - 363
AU - Jianyong DUAN
AU - Liangcai LI
AU - Mei ZHANG
AU - Hao WANG
PY - 2022
DO - 10.1587/transinf.2021EDP7034
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2022
AB - Personalized news recommendation is becoming increasingly important for online news platforms to help users alleviate information overload and improve news reading experience. A key problem in news recommendation is learning accurate user representations to capture their interest. However, most existing news recommendation methods usually learn user representation only from their interacted historical news, while ignoring the clustering features among users. Here we proposed a hierarchical user preference hash network to enhance the representation of users' interest. In the hash part, a series of buckets are generated based on users' historical interactions. Users with similar preferences are assigned into the same buckets automatically. We also learn representations of users from their browsed news in history part. And then, a Route Attention is adopted to combine these two parts (history vector and hash vector) and get the more informative user preference vector. As for news representation, a modified transformer with category embedding is exploited to build news semantic representation. By comparing the hierarchical hash network with multiple news recommendation methods and conducting various experiments on the Microsoft News Dataset (MIND) validate the effectiveness of our approach on news recommendation.
ER -
English
