FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Hongyu, Zheng, Dongyi, Yang, Xu, Feng, Jiyuan, Liao, Qing
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910422315040768
author Zhang, Hongyu
Zheng, Dongyi
Yang, Xu
Feng, Jiyuan
Liao, Qing
author_facet Zhang, Hongyu
Zheng, Dongyi
Yang, Xu
Feng, Jiyuan
Liao, Qing
contents Cross-domain Sequential Recommendation (CSR) which leverages user sequence data from multiple domains has received extensive attention in recent years. However, the existing CSR methods require sharing origin user data across domains, which violates the General Data Protection Regulation (GDPR). Thus, it is necessary to combine federated learning (FL) and CSR to fully utilize knowledge from different domains while preserving data privacy. Nonetheless, the sequence feature heterogeneity across different domains significantly impacts the overall performance of FL. In this paper, we propose FedDCSR, a novel federated cross-domain sequential recommendation framework via disentangled representation learning. Specifically, to address the sequence feature heterogeneity across domains, we introduce an approach called inter-intra domain sequence representation disentanglement (SRD) to disentangle the user sequence features into domain-shared and domain-exclusive features. In addition, we design an intra domain contrastive infomax (CIM) strategy to learn richer domain-exclusive features of users by performing data augmentation on user sequences. Extensive experiments on three real-world scenarios demonstrate that FedDCSR achieves significant improvements over existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2309_08420
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning
Zhang, Hongyu
Zheng, Dongyi
Yang, Xu
Feng, Jiyuan
Liao, Qing
Machine Learning
Information Retrieval
Cross-domain Sequential Recommendation (CSR) which leverages user sequence data from multiple domains has received extensive attention in recent years. However, the existing CSR methods require sharing origin user data across domains, which violates the General Data Protection Regulation (GDPR). Thus, it is necessary to combine federated learning (FL) and CSR to fully utilize knowledge from different domains while preserving data privacy. Nonetheless, the sequence feature heterogeneity across different domains significantly impacts the overall performance of FL. In this paper, we propose FedDCSR, a novel federated cross-domain sequential recommendation framework via disentangled representation learning. Specifically, to address the sequence feature heterogeneity across domains, we introduce an approach called inter-intra domain sequence representation disentanglement (SRD) to disentangle the user sequence features into domain-shared and domain-exclusive features. In addition, we design an intra domain contrastive infomax (CIM) strategy to learn richer domain-exclusive features of users by performing data augmentation on user sequences. Extensive experiments on three real-world scenarios demonstrate that FedDCSR achieves significant improvements over existing baselines.
title FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning
topic Machine Learning
Information Retrieval
url https://arxiv.org/abs/2309.08420