Contrastive Learning-Based Personalized Tag Recommendation

Personalized tag recommendation algorithms generate personalized tag lists for users by learning the tagging preferences of users. Traditional personalized tag recommendation systems are limited by the problem of data sparsity, making the personalized tag recommendation models unable to accurately l...

Full description

Saved in:
Bibliographic Details
Main Authors: Aoran Zhang, Yonghong Yu, Shenglong Li, Rong Gao, Li Zhang, Shang Gao
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/18/6061
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259485087498240
author Aoran Zhang
Yonghong Yu
Shenglong Li
Rong Gao
Li Zhang
Shang Gao
author_facet Aoran Zhang
Yonghong Yu
Shenglong Li
Rong Gao
Li Zhang
Shang Gao
author_sort Aoran Zhang
collection DOAJ
description Personalized tag recommendation algorithms generate personalized tag lists for users by learning the tagging preferences of users. Traditional personalized tag recommendation systems are limited by the problem of data sparsity, making the personalized tag recommendation models unable to accurately learn the embeddings of users, items, and tags. To address this issue, we propose a contrastive learning-based personalized tag recommendation algorithm, namely CLPTR. Specifically, CLPTR generates augmented views of user–tag and item–tag interaction graphs by injecting noises into implicit feature representations rather than dropping nodes and edges. Hence, CLPTR is able to greatly preserve the underlying semantics of the original user–tag or the item–tag interaction graphs and avoid destroying their structural information. In addition, we integrate the contrastive learning module into a graph neural network-based personalized tag recommendation model, which enables the model to extract self-supervised signals from user–tag and item–tag interaction graphs. We conduct extensive experiments on real-world datasets, and the experimental results demonstrate the state-of-the-art performance of our proposed CLPTR compared with traditional personalized tag recommendation models.
format Article
id doaj-art-ff3f093bf6e84bd38da28a3d779901d0
institution OA Journals
issn 1424-8220
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-ff3f093bf6e84bd38da28a3d779901d02025-08-20T01:55:51ZengMDPI AGSensors1424-82202024-09-012418606110.3390/s24186061Contrastive Learning-Based Personalized Tag RecommendationAoran Zhang0Yonghong Yu1Shenglong Li2Rong Gao3Li Zhang4Shang Gao5School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212000, ChinaCollege of Tongda, Nanjing University of Posts and Telecommunication, Yangzhou 225127, ChinaCollege of Tongda, Nanjing University of Posts and Telecommunication, Yangzhou 225127, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaDepartment of Computer Science, Royal Holloway University of London, Egham TW20 0EX, UKSchool of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212000, ChinaPersonalized tag recommendation algorithms generate personalized tag lists for users by learning the tagging preferences of users. Traditional personalized tag recommendation systems are limited by the problem of data sparsity, making the personalized tag recommendation models unable to accurately learn the embeddings of users, items, and tags. To address this issue, we propose a contrastive learning-based personalized tag recommendation algorithm, namely CLPTR. Specifically, CLPTR generates augmented views of user–tag and item–tag interaction graphs by injecting noises into implicit feature representations rather than dropping nodes and edges. Hence, CLPTR is able to greatly preserve the underlying semantics of the original user–tag or the item–tag interaction graphs and avoid destroying their structural information. In addition, we integrate the contrastive learning module into a graph neural network-based personalized tag recommendation model, which enables the model to extract self-supervised signals from user–tag and item–tag interaction graphs. We conduct extensive experiments on real-world datasets, and the experimental results demonstrate the state-of-the-art performance of our proposed CLPTR compared with traditional personalized tag recommendation models.https://www.mdpi.com/1424-8220/24/18/6061contrastive learninggraph neural networkpersonalized tag recommendation
spellingShingle Aoran Zhang
Yonghong Yu
Shenglong Li
Rong Gao
Li Zhang
Shang Gao
Contrastive Learning-Based Personalized Tag Recommendation
Sensors
contrastive learning
graph neural network
personalized tag recommendation
title Contrastive Learning-Based Personalized Tag Recommendation
title_full Contrastive Learning-Based Personalized Tag Recommendation
title_fullStr Contrastive Learning-Based Personalized Tag Recommendation
title_full_unstemmed Contrastive Learning-Based Personalized Tag Recommendation
title_short Contrastive Learning-Based Personalized Tag Recommendation
title_sort contrastive learning based personalized tag recommendation
topic contrastive learning
graph neural network
personalized tag recommendation
url https://www.mdpi.com/1424-8220/24/18/6061
work_keys_str_mv AT aoranzhang contrastivelearningbasedpersonalizedtagrecommendation
AT yonghongyu contrastivelearningbasedpersonalizedtagrecommendation
AT shenglongli contrastivelearningbasedpersonalizedtagrecommendation
AT ronggao contrastivelearningbasedpersonalizedtagrecommendation
AT lizhang contrastivelearningbasedpersonalizedtagrecommendation
AT shanggao contrastivelearningbasedpersonalizedtagrecommendation