METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation

In recent years, there has been a burgeoning interest in multimodal recommender systems, which integrate various data types to achieve more personalized recommendations. Despite this, the effective incorporation of user preferences for multimodal data and the exploration of inherent semantic relatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunfei Zhao, Jie Guo, Longyu Wen, Letian Wang
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-05-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949715925000150
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850120296920514560
author Yunfei Zhao
Jie Guo
Longyu Wen
Letian Wang
author_facet Yunfei Zhao
Jie Guo
Longyu Wen
Letian Wang
author_sort Yunfei Zhao
collection DOAJ
description In recent years, there has been a burgeoning interest in multimodal recommender systems, which integrate various data types to achieve more personalized recommendations. Despite this, the effective incorporation of user preferences for multimodal data and the exploration of inherent semantic relationships between modalities still need to be explored. Prior research typically utilizes multimodal data to construct item graphs, often overlooking the nuanced details within the data. As a result, these studies fail to thoroughly examine the semantic relationships between items and user behavioral patterns. Our proposed approach, METRIC, addresses this gap by delving deeper into multimodal information. METRIC consists of two primary modules: the multiple preference modelling (MPM) module and the item semantic enhancement (ISE) module. The ISE module performs relational mining across multiple attributes, leveraging the semantic structural relationships inherent in items. In contrast, the MPM module enables users to articulate their preferences across different modalities and facilitates adaptive fusion through an attention mechanism. This approach not only improves precision in capturing user preferences and interests but also minimizes interference from varying modalities. Our extensive experiments on three benchmark datasets substantiate METRIC's superiority and the efficacy of its core components.
format Article
id doaj-art-cd4eb0eee3d34689a223eac2e9efdf1e
institution OA Journals
issn 2949-7159
language English
publishDate 2025-05-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-cd4eb0eee3d34689a223eac2e9efdf1e2025-08-20T02:35:23ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592025-05-013324225610.1016/j.jiixd.2025.04.001METRIC: Multiple preferences learning with refined item attributes for multimodal recommendationYunfei Zhao0Jie Guo1Longyu Wen2Letian Wang3State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an 710071, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi'an 710071, China; Corresponding author.Hangzhou Institute of Technology, Xidian University, Hangzhou 311231, ChinaHangzhou Institute of Technology, Xidian University, Hangzhou 311231, ChinaIn recent years, there has been a burgeoning interest in multimodal recommender systems, which integrate various data types to achieve more personalized recommendations. Despite this, the effective incorporation of user preferences for multimodal data and the exploration of inherent semantic relationships between modalities still need to be explored. Prior research typically utilizes multimodal data to construct item graphs, often overlooking the nuanced details within the data. As a result, these studies fail to thoroughly examine the semantic relationships between items and user behavioral patterns. Our proposed approach, METRIC, addresses this gap by delving deeper into multimodal information. METRIC consists of two primary modules: the multiple preference modelling (MPM) module and the item semantic enhancement (ISE) module. The ISE module performs relational mining across multiple attributes, leveraging the semantic structural relationships inherent in items. In contrast, the MPM module enables users to articulate their preferences across different modalities and facilitates adaptive fusion through an attention mechanism. This approach not only improves precision in capturing user preferences and interests but also minimizes interference from varying modalities. Our extensive experiments on three benchmark datasets substantiate METRIC's superiority and the efficacy of its core components.http://www.sciencedirect.com/science/article/pii/S2949715925000150Multimodal recommendationGraph convolution networkEmbedding enhancementPreference enhancement
spellingShingle Yunfei Zhao
Jie Guo
Longyu Wen
Letian Wang
METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation
Journal of Information and Intelligence
Multimodal recommendation
Graph convolution network
Embedding enhancement
Preference enhancement
title METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation
title_full METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation
title_fullStr METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation
title_full_unstemmed METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation
title_short METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation
title_sort metric multiple preferences learning with refined item attributes for multimodal recommendation
topic Multimodal recommendation
Graph convolution network
Embedding enhancement
Preference enhancement
url http://www.sciencedirect.com/science/article/pii/S2949715925000150
work_keys_str_mv AT yunfeizhao metricmultiplepreferenceslearningwithrefineditemattributesformultimodalrecommendation
AT jieguo metricmultiplepreferenceslearningwithrefineditemattributesformultimodalrecommendation
AT longyuwen metricmultiplepreferenceslearningwithrefineditemattributesformultimodalrecommendation
AT letianwang metricmultiplepreferenceslearningwithrefineditemattributesformultimodalrecommendation