RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems

TL;DR

RecSys-DAN introduces a novel adversarial transfer learning approach for cross-domain recommender systems that effectively addresses data sparsity and imbalance, improving cold-start recommendations without requiring labeled target domain data.

Contribution

It proposes a new adversarial neural network framework that transfers latent representations across domains, enhancing recommendation performance in sparse and imbalanced data scenarios.

Findings

Achieves competitive performance without labeled target data

Effective in unimodal and multimodal scenarios

Improves cold-start recommendation robustness

Abstract

Data sparsity and data imbalance are practical and challenging issues in cross-domain recommender systems. This paper addresses those problems by leveraging the concepts which derive from representation learning, adversarial learning and transfer learning (particularly, domain adaptation). Although various transfer learning methods have shown promising performance in this context, our proposed novel method RecSys-DAN focuses on alleviating the cross-domain and within-domain data sparsity and data imbalance and learns transferable latent representations for users, items and their interactions. Different from existing approaches, the proposed method transfers the latent representations from a source domain to a target domain in an adversarial way. The mapping functions in the target domain are learned by playing a min-max game with an adversarial loss, aiming to generate domain indistinguishable representations for a discriminator. Four neural architectural instances of ResSys-DAN are proposed and explored. Empirical results on real-world Amazon data show that, even without using labeled data (i.e., ratings) in the target domain, RecSys-DAN achieves competitive performance as compared to the state-of-the-art supervised methods. More importantly, RecSys-DAN is highly flexible to both unimodal and multimodal scenarios, and thus it is more robust to the cold-start recommendation which is difficult for previous methods.