IEICE TRANSACTIONS on Information
Collaborative Filtering Auto-Encoders for Technical Patent Recommending
Summary :
To find the exact items from the massive patent resources for users is a matter of great urgency. Although the recommender systems have shot this problem to a certain extent, there are still some challenging problems, such as tracking user interests and improving the recommendation quality when the rating matrix is extremely sparse. In this paper, we propose a novel method called Collaborative Filtering Auto-Encoder for the top-N recommendation. This method employs Auto-Encoders to extract the item's features, converts a high-dimensional sparse vector into a low-dimensional dense vector, and then uses the dense vector for similarity calculation. At the same time, to make the recommendation list closer to the user's recent interests, we divide the recommendation weight into time-based and recent similarity-based weights. In fact, the proposed method is an improved, item-based collaborative filtering model with more flexible components. Experimental results show that the method consistently outperforms state-of-the-art top-N recommendation methods by a significant margin on standard evaluation metrics.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.8 pp.1258-1265
- Publication Date
- 2021/08/01
- Publicized
- 2021/04/26
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2020BDP0014
- Type of Manuscript
- Special Section PAPER (Special Section on Computational Intelligence and Big Data for Scientific and Technological Resources and Services)
- Category
Authors
Wenlei BAI
Northwest University
Jun GUO
Northwest University
Xueqing ZHANG
Northwest University
Baoying LIU
Northwest University
Daguang GAN
Wanfang Data
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
Wenlei BAI, Jun GUO, Xueqing ZHANG, Baoying LIU, Daguang GAN, "Collaborative Filtering Auto-Encoders for Technical Patent Recommending" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 8, pp. 1258-1265, August 2021, doi: 10.1587/transinf.2020BDP0014.
Abstract: To find the exact items from the massive patent resources for users is a matter of great urgency. Although the recommender systems have shot this problem to a certain extent, there are still some challenging problems, such as tracking user interests and improving the recommendation quality when the rating matrix is extremely sparse. In this paper, we propose a novel method called Collaborative Filtering Auto-Encoder for the top-N recommendation. This method employs Auto-Encoders to extract the item's features, converts a high-dimensional sparse vector into a low-dimensional dense vector, and then uses the dense vector for similarity calculation. At the same time, to make the recommendation list closer to the user's recent interests, we divide the recommendation weight into time-based and recent similarity-based weights. In fact, the proposed method is an improved, item-based collaborative filtering model with more flexible components. Experimental results show that the method consistently outperforms state-of-the-art top-N recommendation methods by a significant margin on standard evaluation metrics.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020BDP0014/_p
Copy
@ARTICLE{e104-d_8_1258,
author={Wenlei BAI, Jun GUO, Xueqing ZHANG, Baoying LIU, Daguang GAN, },
journal={IEICE TRANSACTIONS on Information},
title={Collaborative Filtering Auto-Encoders for Technical Patent Recommending},
year={2021},
volume={E104-D},
number={8},
pages={1258-1265},
abstract={To find the exact items from the massive patent resources for users is a matter of great urgency. Although the recommender systems have shot this problem to a certain extent, there are still some challenging problems, such as tracking user interests and improving the recommendation quality when the rating matrix is extremely sparse. In this paper, we propose a novel method called Collaborative Filtering Auto-Encoder for the top-N recommendation. This method employs Auto-Encoders to extract the item's features, converts a high-dimensional sparse vector into a low-dimensional dense vector, and then uses the dense vector for similarity calculation. At the same time, to make the recommendation list closer to the user's recent interests, we divide the recommendation weight into time-based and recent similarity-based weights. In fact, the proposed method is an improved, item-based collaborative filtering model with more flexible components. Experimental results show that the method consistently outperforms state-of-the-art top-N recommendation methods by a significant margin on standard evaluation metrics.},
keywords={},
doi={10.1587/transinf.2020BDP0014},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - Collaborative Filtering Auto-Encoders for Technical Patent Recommending
T2 - IEICE TRANSACTIONS on Information
SP - 1258
EP - 1265
AU - Wenlei BAI
AU - Jun GUO
AU - Xueqing ZHANG
AU - Baoying LIU
AU - Daguang GAN
PY - 2021
DO - 10.1587/transinf.2020BDP0014
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2021
AB - To find the exact items from the massive patent resources for users is a matter of great urgency. Although the recommender systems have shot this problem to a certain extent, there are still some challenging problems, such as tracking user interests and improving the recommendation quality when the rating matrix is extremely sparse. In this paper, we propose a novel method called Collaborative Filtering Auto-Encoder for the top-N recommendation. This method employs Auto-Encoders to extract the item's features, converts a high-dimensional sparse vector into a low-dimensional dense vector, and then uses the dense vector for similarity calculation. At the same time, to make the recommendation list closer to the user's recent interests, we divide the recommendation weight into time-based and recent similarity-based weights. In fact, the proposed method is an improved, item-based collaborative filtering model with more flexible components. Experimental results show that the method consistently outperforms state-of-the-art top-N recommendation methods by a significant margin on standard evaluation metrics.
ER -
English
