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

Abstract

Collaborative Filtering (CF) is a widely adopted technique in recommender systems. Traditional CF models mainly focus on predicting a user's preference to the items in a single domain such as the movie domain or the music domain. A major challenge for such models is the data sparsity problem, and especially, CF cannot make accurate predictions for the cold-start users who have no ratings at all. Although Cross-Domain Collaborative Filtering (CDCF) is proposed for effectively transferring users' rating preference across different domains, it is still difficult for existing CDCF models to tackle the cold-start users in the target domain due to the extreme data sparsity. In this paper, we propose a Cross-Domain Latent Feature Mapping (CDLFM) model for cold-start users in the target domain. Firstly, in order to better characterize users in sparse domains, we take the users' similarity relationship on rating behaviors into consideration and propose the Matrix Factorization by incorporating User Similarities (MFUS) in which three similarity measures are proposed. Next, to perform knowledge transfer across domains, we propose a neighborhood based gradient boosting trees method to learn the cross-domain user latent feature mapping function. For each cold-start user, we learn his/her feature mapping function based on the latent feature pairs of those linked users who have similar rating behaviors with the cold-start user in the auxiliary domain. And the preference of the cold-start user in the target domain can be predicted based on the mapping function and his/her latent features in the auxiliary domain. Experimental results on two real datasets extracted from Amazon transaction data demonstrate the superiority of our proposed model against other state-of-the-art methods.

Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems

“…Unfortunately, recommendation algorithms are generally faced with data sparsity and cold start problems in that a user's feedback usually merely involves an extremely tiny part of the commodities on a website. As a promising solution to address these issues, cross-domain recommendation algorithms (Song et al 2017;Wang et al 2018) have gained increasing attention in recent years. This kind of algorithm tries to utilize explicit or implicit feedbacks from multiple auxiliary domains to improve the recommendation performance in the target domain.…”

Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

“…[6] calibrates domain-specific graph Laplacians into a unified kernel, which detects graph patterns in semi-supervised fashion. [37] introduces a matrix factorization approach on two bipartite graphs simultaneously to measure the similarity between their shared nodes. [28] operates multi-layer spectral convolutions on different graphs to learn node communities.…”

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.…”

“…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.…”

“…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.…”