arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.09286cs.LG
收藏

基于多源异构迁移学习的跨域推荐集中式-分布式迁移模型

A Centralized-Distributed Transfer Model for Cross-Domain Recommendation Based on Multi-Source Heterogeneous Transfer Learning

Hangzhou NetEase Cloud Music Technology Co., Ltd.(杭州网易云音乐科技有限公司)

Ke Xu, Ziliang Wang, Wei Zheng, Yuhao Ma, Chenglin Wang, Nengxue Jiang, Cai Cao

AI总结:

针对跨域推荐中多源异构性问题,提出基于多源异构迁移学习的集中式-分布式迁移模型(CDTM),通过双重嵌入结构和注意力机制有效融合多源知识,提升目标域推荐性能。

摘要:

跨域推荐(CDR)方法被提出以解决点击率(CTR)估计中的稀疏性问题。现有CDR方法直接将知识从源域迁移到目标域,忽略了域之间的异构性,包括特征维度异构性和潜在空间异构性,这可能导致负迁移。此外,现有大多数方法基于单源迁移,无法同时利用多个源域的知识进一步提升模型在目标域的性能。本文提出一种基于多源异构迁移学习的CDR集中式-分布式迁移模型(CDTM)。为解决特征维度异构性问题,构建了双重嵌入结构:域特定嵌入(DSE)和全局共享嵌入(GSE),分别建模单域特征表示和全局空间共性。为解决潜在空间异构性,使用迁移矩阵和注意力机制自适应地映射和组合DSE与GSE。大量离线和在线实验验证了模型的有效性。

英文摘要:

Cross-domain recommendation (CDR) methods are proposed to tackle the sparsity problem in click through rate (CTR) estimation. Existing CDR methods directly transfer knowledge from the source domains to the target domain and ignore the heterogeneities among domains, including feature dimensional heterogeneity and latent space heterogeneity, which may lead to negative transfer. Besides, most of the existing methods are based on single-source transfer, which cannot simultaneously utilize knowledge from multiple source domains to further improve the model performance in the target domain. In this paper, we propose a centralized-distributed transfer model (CDTM) for CDR based on multi-source heterogeneous transfer learning. To address the issue of feature dimension heterogeneity, we build a dual embedding structure: domain specific embedding (DSE) and global shared embedding (GSE) to model the feature representation in the single domain and the commonalities in the global space,separately. To solve the latent space heterogeneity, the transfer matrix and attention mechanism are used to map and combine DSE and GSE adaptively. Extensive offline and online experiments demonstrate the effectiveness of our model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑