Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation

Knowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constru...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingchen Liu, Guangyuan Dong, Zihao Li, Yuanyuan Fang, Jingchen Li, Wenqi Sun, Bohan Zhang, Changzhi Li, Xin Li
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/15/2496
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406078378311680
author Bingchen Liu
Guangyuan Dong
Zihao Li
Yuanyuan Fang
Jingchen Li
Wenqi Sun
Bohan Zhang
Changzhi Li
Xin Li
author_facet Bingchen Liu
Guangyuan Dong
Zihao Li
Yuanyuan Fang
Jingchen Li
Wenqi Sun
Bohan Zhang
Changzhi Li
Xin Li
author_sort Bingchen Liu
collection DOAJ
description Knowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constructed from users’ historical interaction data now incorporates multiattribute information, including timestamps, images, and textual content. The information of multiple modalities is difficult to effectively utilize due to their different representation structures and spaces. The existing methods attempt to utilize the above information through simple embedding representation and aggregation, but ignore targeted representation learning for information with different attributes and learning effective weights for aggregation. In addition, existing methods are not sufficient for effectively modeling temporal information. In this article, we propose MTR, a knowledge graph recommendation framework based on mixture of experts network. To achieve this goal, we use a mixture-of-experts network to learn targeted representations and weights of different product attributes for effective modeling and utilization. In addition, we effectively model the temporal information during the user shopping process. A thorough experimental study on popular benchmarks validates that MTR can achieve competitive results.
format Article
id doaj-art-7dcd5abaa12f44c6a3a181b3abdd46e7
institution Kabale University
issn 2227-7390
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-7dcd5abaa12f44c6a3a181b3abdd46e72025-08-20T03:36:31ZengMDPI AGMathematics2227-73902025-08-011315249610.3390/math13152496Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for RecommendationBingchen Liu0Guangyuan Dong1Zihao Li2Yuanyuan Fang3Jingchen Li4Wenqi Sun5Bohan Zhang6Changzhi Li7Xin Li8School of Software, Shandong University, Jinan 250101, ChinaDepartment of Statistics and Data Science, National University of Singapore, Singapore 119077, SingaporeSchool of Mathematics and Physics, Xi’an Jiaotong-Liverpool University, Suzhou 215028, ChinaMetropolitan College, Boston University, Boston, MA 02215, USASchool of Software, Shandong University, Jinan 250101, ChinaSchool of Computer and Artificial Intelligence, Shandong University of Finance and Economics, Jinan 250020, ChinaCollege of Electronic Engineering, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaIEIT SYSTEMS Co., Ltd., Jinan 250000, ChinaSchool of Software, Shandong University, Jinan 250101, ChinaKnowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constructed from users’ historical interaction data now incorporates multiattribute information, including timestamps, images, and textual content. The information of multiple modalities is difficult to effectively utilize due to their different representation structures and spaces. The existing methods attempt to utilize the above information through simple embedding representation and aggregation, but ignore targeted representation learning for information with different attributes and learning effective weights for aggregation. In addition, existing methods are not sufficient for effectively modeling temporal information. In this article, we propose MTR, a knowledge graph recommendation framework based on mixture of experts network. To achieve this goal, we use a mixture-of-experts network to learn targeted representations and weights of different product attributes for effective modeling and utilization. In addition, we effectively model the temporal information during the user shopping process. A thorough experimental study on popular benchmarks validates that MTR can achieve competitive results.https://www.mdpi.com/2227-7390/13/15/2496knowledge graphmixture of expertsmultimodal knowledge graph
spellingShingle Bingchen Liu
Guangyuan Dong
Zihao Li
Yuanyuan Fang
Jingchen Li
Wenqi Sun
Bohan Zhang
Changzhi Li
Xin Li
Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation
Mathematics
knowledge graph
mixture of experts
multimodal knowledge graph
title Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation
title_full Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation
title_fullStr Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation
title_full_unstemmed Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation
title_short Multimodal Temporal Knowledge Graph Embedding Method Based on Mixture of Experts for Recommendation
title_sort multimodal temporal knowledge graph embedding method based on mixture of experts for recommendation
topic knowledge graph
mixture of experts
multimodal knowledge graph
url https://www.mdpi.com/2227-7390/13/15/2496
work_keys_str_mv AT bingchenliu multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT guangyuandong multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT zihaoli multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT yuanyuanfang multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT jingchenli multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT wenqisun multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT bohanzhang multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT changzhili multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation
AT xinli multimodaltemporalknowledgegraphembeddingmethodbasedonmixtureofexpertsforrecommendation