DDTCDR: Deep Dual Transfer Cross Domain Recommendation

TL;DR

This paper introduces DDTCDR, a novel deep dual transfer learning model for cross-domain recommendation systems that effectively captures bidirectional user-item relations and incorporates feature information, outperforming existing methods.

Contribution

The paper proposes a dual learning-based approach with a latent orthogonal mapping and autoencoder integration for improved cross-domain recommendations.

Findings

Significantly outperforms state-of-the-art baselines.

Effective in three diverse domains: movies, books, music.

Demonstrates stability and robustness in recommendation accuracy.

Abstract

Cross domain recommender systems have been increasingly valuable for helping consumers identify the most satisfying items from different categories. However, previously proposed cross-domain models did not take into account bidirectional latent relations between users and items. In addition, they do not explicitly model information of user and item features, while utilizing only user ratings information for recommendations. To address these concerns, in this paper we propose a novel approach to cross-domain recommendations based on the mechanism of dual learning that transfers information between two related domains in an iterative manner until the learning process stabilizes. We develop a novel latent orthogonal mapping to extract user preferences over multiple domains while preserving relations between users across different latent spaces. Combining with autoencoder approach to extract the latent essence of feature information, we propose Deep Dual Transfer Cross Domain Recommendation (DDTCDR) model to provide recommendations in respective domains. We test the proposed method on a large dataset containing three domains of movies, book and music items and demonstrate that it consistently and significantly outperforms several state-of-the-art baselines and also classical transfer learning approaches.