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

TL;DR

This paper introduces a novel transfer learning model for cross-domain recommendation that effectively handles domain heterogeneities and leverages multiple sources to improve CTR prediction.

Contribution

It proposes a centralized-distributed transfer model with dual embedding structures and adaptive mapping to address feature and latent space heterogeneities in multi-source CDR.

Findings

Model outperforms existing methods in offline and online tests.

Effectively mitigates negative transfer due to domain heterogeneities.

Utilizes multiple source domains to enhance target domain recommendation.

Abstract

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.