A hinge-loss based codebook transfer for cross-domain recommendation with non-overlapping data. Issue 107 (July 2022)

• Record Type: Journal Article
• Authors: Veeramachaneni, Sowmini Devi; Pujari, Arun K.; Padmanabhan, Vineet; Kumar, Vikas
• Is Part Of: Information systems. Issue 107(2022)
• Publication Date: 2022-07
• Subjects: Collaborative filtering -- Matrix factorisation -- Codebook -- Transfer learning -- Cross-domain recommender systems; Database management -- Periodicals; Electronic data processing -- Periodicals; Bases de données -- Gestion -- Périodiques; Informatique -- Périodiques; Database management; Electronic data processing; Periodicals; 005.7
• DOI: 10.1016/j.is.2022.102002
• Languages: English
• ISSNs: 0306-4379

Abstract

Abstract: Recommender systems, especially collaborative filtering (CF) based recommender systems, has been playing an important role in many e-commerce applications. As the information being searched over the internet is rapidly increasing, users often face the difficulty of finding items of his/her own interest and recommender systems often provides help in such tasks. Recent studies show that, as the item space increases, and the number of items rated by the users become very less, issues like sparsity arise. To mitigate the sparsity problem, transfer learning techniques are being used wherein the data from dense domain (source) is considered in order to predict the missing entries in the sparse domain (target). In this paper, we propose a novel transfer learning approach called T ransfer of C odebook via H inge loss or TCH for cross-domain recommendation when both domains have no overlap of users and items. In our approach constructing the codebook and transferring the same knowledge from source to target domain is done in a novel way. We employ a similar formulation of co-clustering technique to obtain the codebook (cluster-level rating pattern) of source domain. By making use of hinge loss function we transfer the learnt codebook of the source domain to target. The use of hinge loss as a loss function is novel and has not been tried before in transfer learning. We demonstrate that our technique improves the approximation of the target matrix on benchmark datasets. Highlights: We propose a model for cross-domain recommendation to address the data sparsity. The proposed method is useful when the domains do not share common users or items. Co-clustering technique is used to construct the codebook from the source domain. Learnt codebook gets transferred to the target domain in a novel way via hinge loss. We validate the performance of the proposed method on benchmark datasets.