Cross-Domain Recommendation: An Embedding and Mapping Approach

Abstract

Data sparsity is one of the most challenging problems for recommender systems. One promising solution to this problem is cross-domain recommendation, i.e., leveraging feedbacks or ratings from multiple domains to improve recommendation performance in a collective manner. In this paper, we propose an Embedding and Mapping framework for Cross-Domain Recommendation, called EMCDR. The proposed EMCDR framework distinguishes itself from existing crossdomain recommendation models in two aspects. First, a multi-layer perceptron is used to capture the nonlinear mapping function across domains, which offers high flexibility for learning domain-specific features of entities in each domain. Second, only the entities with sufficient data are used to learn the mapping function, guaranteeing its robustness to noise caused by data sparsity in single domain. Extensive experiments on two cross-domain recommendation scenarios demonstrate that EMCDR significantly outperforms stateof-the-art cross-domain recommendation methods.

Cross-Domain Recommendation for Cold-Start Users via Neighborhood Based Feature Mapping

“…Hu [20] mentions the unacquainted world for users and propose CDTF to capture the triadic relation of user-item-domain by tensor factorization. EMCDR [21] and [22] try to use the Multi-Layer Perceptron (MLP) and a transformation matrix to map the user feature vector across domains, but they take all the linked users into consideration which may introduce noise. On social networks [23], the cold start problem has been widely studied.…”

JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation

“…Broad Learning [7] is a way to transfer the information from different domains, which focuses on fusing and mining multiple information sources of large volumes and diverse varieties. To solve the cold-start problem in item recommendation, cross-domain recommendation is proposed by either learning shallow embedding with factorization machine [8], [10], [33], [34] or learning deep embedding with neural networks [4], [9], [35]- [37]. When learning shallow embedding, CMF [33] jointly factorizes the user-item interaction matrices from different domains.…”

“…Recommending users with a set of preferred items is still an open problem [1]- [6], especially when the dataset is very sparse. To remedy the data sparsity issue, broad-leraning based model [7] and cross-domain recommender system [4], [8] are proposed where the information from other source domains can be transferred to the target domain. To transfer the knowledge from one domain to another, one can use the overlapping users [4], [6], [8], [9] in two ways: (1) the neighborhood information of common users stores the structure information of different domains with which we can do cross-domain recommendation [6], [10]; or (2) we can learn a mapping function [4], [8] to project latent vectors learned in one domain into another, and thus the knowledge can be transferred.…”

“…The information from the source domain cannot be directly utilized in the target domain. Thus we need to propose some mapping methods [4], [18], [19] as a bridge for the information transferring.…”

“…In this paper, unlike previous direct mapping methods [4], [10], [18], we view the latent vectors of a user in a specific domain as an interest projection from a domain-invariant representation. We show an illustration of mapping the domaininvariant user representation to a domain-specific user latent vectors in Fig.…”