Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph

To alleviate the cold-start problem that exists in traditional collaborative filtering recommendation systems, knowledge graphs have been introduced as a kind of auxiliary knowledge in recommendation systems. However, existing knowledge graph recommendation models have limitations in adequately mode...

Full description

Saved in:
Bibliographic Details
Main Author: ZHOU Jiaxuan, LIU Xianhui, ZHAO Xiaodong, HOU Wenlong, ZHAO Weidong
Format: Article
Language:zho
Published: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2025-05-01
Series:Jisuanji kexue yu tansuo
Subjects:
Online Access:http://fcst.ceaj.org/fileup/1673-9418/PDF/2406021.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849313472827883520
author ZHOU Jiaxuan, LIU Xianhui, ZHAO Xiaodong, HOU Wenlong, ZHAO Weidong
author_facet ZHOU Jiaxuan, LIU Xianhui, ZHAO Xiaodong, HOU Wenlong, ZHAO Weidong
author_sort ZHOU Jiaxuan, LIU Xianhui, ZHAO Xiaodong, HOU Wenlong, ZHAO Weidong
collection DOAJ
description To alleviate the cold-start problem that exists in traditional collaborative filtering recommendation systems, knowledge graphs have been introduced as a kind of auxiliary knowledge in recommendation systems. However, existing knowledge graph recommendation models have limitations in adequately modeling higher-order interactions, making it difficult to capture important information from higher-order neighbors. In addition, the sparsity problem of supervised signals also affects recommendation system performance. To address the above issues, a self-supervised knowledge-aware recommendation model integrating adaptive hypergraph is proposed. The model first utilizes a hybrid graph convolutional network to jointly learn the low-order interaction embeddings in the interaction graph and the higher-order interaction embeddings in the adaptive hypergraph. Secondly, it uses a relation-aware graph attention network to mine the rich knowledge information of users and items in the knowledge graph. Then, the model constructs a comparison learning task based on the three views, which mitigates the sparsity problem of the interaction data by introducing the self-supervised signals. Finally, the three kinds of embeddings are combined for subsequent recommendation prediction. The model is experimentally compared with benchmark models such as KGAT, KGIN, and KACL on several publicly available datasets. Compared with the best recommendation performance model among the seven compared models, on the MovieLens dataset, Recall@20 is improved by 1.22%, NDCG@20 is improved by 1.17%; on the Yelp2018 dataset, Recall@20 is improved by 1.41%, NDCG@20 is improved by 1.60%. Experimental results show that this model outperforms other benchmark models in terms of recommendation performance.
format Article
id doaj-art-74ba2a9253484eae82a2f7f6c20665af
institution Kabale University
issn 1673-9418
language zho
publishDate 2025-05-01
publisher Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
record_format Article
series Jisuanji kexue yu tansuo
spelling doaj-art-74ba2a9253484eae82a2f7f6c20665af2025-08-20T03:52:43ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182025-05-011951217122910.3778/j.issn.1673-9418.2406021Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive HypergraphZHOU Jiaxuan, LIU Xianhui, ZHAO Xiaodong, HOU Wenlong, ZHAO Weidong0School of Electronic and Information Engineering, Tongji University, Shanghai 201804, ChinaTo alleviate the cold-start problem that exists in traditional collaborative filtering recommendation systems, knowledge graphs have been introduced as a kind of auxiliary knowledge in recommendation systems. However, existing knowledge graph recommendation models have limitations in adequately modeling higher-order interactions, making it difficult to capture important information from higher-order neighbors. In addition, the sparsity problem of supervised signals also affects recommendation system performance. To address the above issues, a self-supervised knowledge-aware recommendation model integrating adaptive hypergraph is proposed. The model first utilizes a hybrid graph convolutional network to jointly learn the low-order interaction embeddings in the interaction graph and the higher-order interaction embeddings in the adaptive hypergraph. Secondly, it uses a relation-aware graph attention network to mine the rich knowledge information of users and items in the knowledge graph. Then, the model constructs a comparison learning task based on the three views, which mitigates the sparsity problem of the interaction data by introducing the self-supervised signals. Finally, the three kinds of embeddings are combined for subsequent recommendation prediction. The model is experimentally compared with benchmark models such as KGAT, KGIN, and KACL on several publicly available datasets. Compared with the best recommendation performance model among the seven compared models, on the MovieLens dataset, Recall@20 is improved by 1.22%, NDCG@20 is improved by 1.17%; on the Yelp2018 dataset, Recall@20 is improved by 1.41%, NDCG@20 is improved by 1.60%. Experimental results show that this model outperforms other benchmark models in terms of recommendation performance.http://fcst.ceaj.org/fileup/1673-9418/PDF/2406021.pdfrecommendation system; knowledge graph; adaptive hypergraph; self-supervised learning; relation-aware graph attention network
spellingShingle ZHOU Jiaxuan, LIU Xianhui, ZHAO Xiaodong, HOU Wenlong, ZHAO Weidong
Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph
Jisuanji kexue yu tansuo
recommendation system; knowledge graph; adaptive hypergraph; self-supervised learning; relation-aware graph attention network
title Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph
title_full Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph
title_fullStr Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph
title_full_unstemmed Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph
title_short Self-Supervised Knowledge-Aware Recommendation Model Integrating Adaptive Hypergraph
title_sort self supervised knowledge aware recommendation model integrating adaptive hypergraph
topic recommendation system; knowledge graph; adaptive hypergraph; self-supervised learning; relation-aware graph attention network
url http://fcst.ceaj.org/fileup/1673-9418/PDF/2406021.pdf
work_keys_str_mv AT zhoujiaxuanliuxianhuizhaoxiaodonghouwenlongzhaoweidong selfsupervisedknowledgeawarerecommendationmodelintegratingadaptivehypergraph