南京师大学报（自然科学版）2026，Vol.49Issue(3)：113-126,14.DOI:10.3969/j.issn.1001-4616.2026.03.013
基于双向解耦知识迁移的跨域推荐算法
Dual Disentangled Knowledge Transfer for Cross-Domain Recommendation
摘要
Abstract
Cross-domain recommendation(CDR)has been proved to be effective to address the long-standing data sparsity and cold-start problems in traditional recommender systems.However,existing methods transfer knowledge at a coarse-grained level,ignoring multiple latent factors behind interactions.To this end,we propose a cross-domain recommendation model named D3-CDR,which enables dual knowledge transfer between domains.Specifically,we design a dual disentangled knowledge transfer layer that consists of several disentangled knowledge transfer(DKT)blocks.In each DKT block,we generate disentangled representations by projecting interaction representations into multiple latent semantic spaces.The attentive knowledge transfer mechanism distills useful knowledge generating cross-domain knowledge representations.The adaptive knowledge fusion mechanism further fuses within-domain knowledge with cross-domain knowledge adaptively.Extensive experiments on two real-world datasets demonstrate the effectiveness of our proposed D3CDR model.关键词
推荐系统/跨域推荐/解耦表示学习/注意力知识迁移/自适应知识融合Key words
recommendation system/cross-domain recommendation/disentangled representation learning/attentive knowledge transfer/adaptive knowledge fusion分类
信息技术与安全科学引用本文复制引用
张春涛,陈奕昕,臧天梓..基于双向解耦知识迁移的跨域推荐算法[J].南京师大学报（自然科学版）,2026,49(3):113-126,14.基金项目
国家自然科学青年科学基金资助项目(62402215)、中车重大资助项目(2025CKA509). （62402215）
