Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning
The cold-start problem has always been a key challenge in the recommendation research field. As a popular method to learn a learner that can rapidly adapt to a new task through a small number of updates, meta-learning is considered to be a feasible algorithm to reduce the error of cold-start recomme...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/2/376 |
_version_ | 1797443454537564160 |
---|---|
author | Shilong Liu Yang Liu Xiaotong Zhang Cheng Xu Jie He Yue Qi |
author_facet | Shilong Liu Yang Liu Xiaotong Zhang Cheng Xu Jie He Yue Qi |
author_sort | Shilong Liu |
collection | DOAJ |
description | The cold-start problem has always been a key challenge in the recommendation research field. As a popular method to learn a learner that can rapidly adapt to a new task through a small number of updates, meta-learning is considered to be a feasible algorithm to reduce the error of cold-start recommendation. However, meta-learning does not take the diverse interests of users into account, which limits the performance improvement in cold-start scenarios. In this paper, we proposed a new model for a cold-start recommendation, which combines the attention mechanism and meta learning. This method enhances the ability of modeling the personalized user interest by learning the weights between users and items based on the attention mechanism and then improves the performance of the cold-start recommendation. We validated the model with two publicly available datasets in the recommendation field. Compared with the three benchmark methods, the proposed model reduces the mean absolute error by at least 2.3% and the root mean square error of 2.5%. |
first_indexed | 2024-03-09T12:57:17Z |
format | Article |
id | doaj.art-d1a2bf61b2ba4c41b2a4fa223d590505 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T12:57:17Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-d1a2bf61b2ba4c41b2a4fa223d5905052023-11-30T21:59:36ZengMDPI AGElectronics2079-92922023-01-0112237610.3390/electronics12020376Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-LearningShilong Liu0Yang Liu1Xiaotong Zhang2Cheng Xu3Jie He4Yue Qi5School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaThe cold-start problem has always been a key challenge in the recommendation research field. As a popular method to learn a learner that can rapidly adapt to a new task through a small number of updates, meta-learning is considered to be a feasible algorithm to reduce the error of cold-start recommendation. However, meta-learning does not take the diverse interests of users into account, which limits the performance improvement in cold-start scenarios. In this paper, we proposed a new model for a cold-start recommendation, which combines the attention mechanism and meta learning. This method enhances the ability of modeling the personalized user interest by learning the weights between users and items based on the attention mechanism and then improves the performance of the cold-start recommendation. We validated the model with two publicly available datasets in the recommendation field. Compared with the three benchmark methods, the proposed model reduces the mean absolute error by at least 2.3% and the root mean square error of 2.5%.https://www.mdpi.com/2079-9292/12/2/376recommendation systemmeta-learningcold-start problemuser preference estimationattention network |
spellingShingle | Shilong Liu Yang Liu Xiaotong Zhang Cheng Xu Jie He Yue Qi Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning Electronics recommendation system meta-learning cold-start problem user preference estimation attention network |
title | Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning |
title_full | Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning |
title_fullStr | Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning |
title_full_unstemmed | Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning |
title_short | Improving the Performance of Cold-Start Recommendation by Fusion of Attention Network and Meta-Learning |
title_sort | improving the performance of cold start recommendation by fusion of attention network and meta learning |
topic | recommendation system meta-learning cold-start problem user preference estimation attention network |
url | https://www.mdpi.com/2079-9292/12/2/376 |
work_keys_str_mv | AT shilongliu improvingtheperformanceofcoldstartrecommendationbyfusionofattentionnetworkandmetalearning AT yangliu improvingtheperformanceofcoldstartrecommendationbyfusionofattentionnetworkandmetalearning AT xiaotongzhang improvingtheperformanceofcoldstartrecommendationbyfusionofattentionnetworkandmetalearning AT chengxu improvingtheperformanceofcoldstartrecommendationbyfusionofattentionnetworkandmetalearning AT jiehe improvingtheperformanceofcoldstartrecommendationbyfusionofattentionnetworkandmetalearning AT yueqi improvingtheperformanceofcoldstartrecommendationbyfusionofattentionnetworkandmetalearning |