Federated cross-view e-commerce recommendation based on feature rescaling

Abstract As big data technologies continue to evolve, recommendation systems have found broad application in domains such as online retail and social networking platforms. However, centralized recommendation systems raise numerous data privacy concerns. Federated learning addresses these concerns by...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruiheng Li, Yuhang Shu, Yue Cao, Yiming Luo, Qiankun Zuo, Xuan Wu, Jiaojiao Yu, Wenxin Zhang
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-81278-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850137053561356288
author Ruiheng Li
Yuhang Shu
Yue Cao
Yiming Luo
Qiankun Zuo
Xuan Wu
Jiaojiao Yu
Wenxin Zhang
author_facet Ruiheng Li
Yuhang Shu
Yue Cao
Yiming Luo
Qiankun Zuo
Xuan Wu
Jiaojiao Yu
Wenxin Zhang
author_sort Ruiheng Li
collection DOAJ
description Abstract As big data technologies continue to evolve, recommendation systems have found broad application in domains such as online retail and social networking platforms. However, centralized recommendation systems raise numerous data privacy concerns. Federated learning addresses these concerns by allowing model training on client devices and aggregating model parameters without sharing raw data. Nevertheless, federated learning faces critical challenges related to feature extraction efficiency and noise sensitivity, limiting its application in e-commerce recommendation systems where data heterogeneity and high-dimensional features are prevalent. To address these gaps, this paper introduces a novel multi-view federated learning framework, Fed-FR-MVD, designed to enhance feature extraction efficiency and improve recommendation accuracy in e-commerce applications. Fed-FR-MVD integrates a FR mechanism within a multi-view structure, incorporating both item and user perspectives to improve feature representation and robustness. This approach yields a 12%–18% increase in recommendation accuracy across various performance metrics compared to single-view and other multi-view methods. By addressing data heterogeneity and optimizing feature utilization through dynamic rescaling, Fed-FR-MVD effectively mitigates the impact of noisy data, with performance maintained across noise levels of 5%–15%. Experimental results demonstrate that Fed-FR-MVD fills a key research gap by providing a more resilient and efficient framework for federated recommendation systems in privacy-sensitive and data-diverse e-commerce environments.
format Article
id doaj-art-577e962a303b42cabd698e0d52b472f4
institution OA Journals
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-577e962a303b42cabd698e0d52b472f42025-08-20T02:30:58ZengNature PortfolioScientific Reports2045-23222024-12-0114111910.1038/s41598-024-81278-1Federated cross-view e-commerce recommendation based on feature rescalingRuiheng Li0Yuhang Shu1Yue Cao2Yiming Luo3Qiankun Zuo4Xuan Wu5Jiaojiao Yu6Wenxin Zhang7Hubei Key Laboratory of Digital Finance Innovation, Hubei University of EconomicsHubei Key Laboratory of Digital Finance Innovation, Hubei University of EconomicsHubei Key Laboratory of Digital Finance Innovation, Hubei University of EconomicsSchool of Information Engineering, Hubei University of EconomicsHubei Key Laboratory of Digital Finance Innovation, Hubei University of EconomicsSchool of Information Engineering, Hubei University of EconomicsHubei Key Laboratory of Digital Finance Innovation, Hubei University of EconomicsSchool of Information Engineering, Hubei University of EconomicsAbstract As big data technologies continue to evolve, recommendation systems have found broad application in domains such as online retail and social networking platforms. However, centralized recommendation systems raise numerous data privacy concerns. Federated learning addresses these concerns by allowing model training on client devices and aggregating model parameters without sharing raw data. Nevertheless, federated learning faces critical challenges related to feature extraction efficiency and noise sensitivity, limiting its application in e-commerce recommendation systems where data heterogeneity and high-dimensional features are prevalent. To address these gaps, this paper introduces a novel multi-view federated learning framework, Fed-FR-MVD, designed to enhance feature extraction efficiency and improve recommendation accuracy in e-commerce applications. Fed-FR-MVD integrates a FR mechanism within a multi-view structure, incorporating both item and user perspectives to improve feature representation and robustness. This approach yields a 12%–18% increase in recommendation accuracy across various performance metrics compared to single-view and other multi-view methods. By addressing data heterogeneity and optimizing feature utilization through dynamic rescaling, Fed-FR-MVD effectively mitigates the impact of noisy data, with performance maintained across noise levels of 5%–15%. Experimental results demonstrate that Fed-FR-MVD fills a key research gap by providing a more resilient and efficient framework for federated recommendation systems in privacy-sensitive and data-diverse e-commerce environments.https://doi.org/10.1038/s41598-024-81278-1Federated learningRecommendation systemsMulti-view frameworkFeature rescalingData privacy
spellingShingle Ruiheng Li
Yuhang Shu
Yue Cao
Yiming Luo
Qiankun Zuo
Xuan Wu
Jiaojiao Yu
Wenxin Zhang
Federated cross-view e-commerce recommendation based on feature rescaling
Scientific Reports
Federated learning
Recommendation systems
Multi-view framework
Feature rescaling
Data privacy
title Federated cross-view e-commerce recommendation based on feature rescaling
title_full Federated cross-view e-commerce recommendation based on feature rescaling
title_fullStr Federated cross-view e-commerce recommendation based on feature rescaling
title_full_unstemmed Federated cross-view e-commerce recommendation based on feature rescaling
title_short Federated cross-view e-commerce recommendation based on feature rescaling
title_sort federated cross view e commerce recommendation based on feature rescaling
topic Federated learning
Recommendation systems
Multi-view framework
Feature rescaling
Data privacy
url https://doi.org/10.1038/s41598-024-81278-1
work_keys_str_mv AT ruihengli federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT yuhangshu federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT yuecao federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT yimingluo federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT qiankunzuo federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT xuanwu federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT jiaojiaoyu federatedcrossviewecommercerecommendationbasedonfeaturerescaling
AT wenxinzhang federatedcrossviewecommercerecommendationbasedonfeaturerescaling