ATLRec: An Attentional Adversarial Transfer Learning Network for Cross-Domain Recommendation

• Published in: Journal of computer science and technology Vol. 35; no. 4; pp. 794 - 808
• Main Authors: Li, Ying, Xu, Jia-Jie, Zhao, Peng-Peng, Fang, Jun-Hua, Chen, Wei, Zhao, Lei
• Format: Journal Article
• Language: English
• Published: Singapore Springer Singapore 01.07.2020; Springer; Springer Nature B.V; School of Computer Science and Technology, Soochow University, Suzhou 215006, China
• Subjects: Artificial Intelligence; Computer Science; Data Structures and Information Theory; Feature extraction; Information Systems Applications (incl.Internet); Knowledge; Learning; Neural networks; Recommender systems; Regular Paper; Representations; Software Engineering; Theory of Computation; cross-domain recommendation; attention mechanism; entity linking; adversarial transfer learning
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-020-0314-8

Entity linking is a new technique in recommender systems to link users’ interaction behaviors in different domains, for the purpose of improving the performance of the recommendation task. Linking-based cross-domain recommendation aims to alleviate the data sparse problem by utilizing the domain-sharable knowledge from auxiliary domains. However, existing methods fail to prevent domain-specific features to be transferred, resulting in suboptimal results. In this paper, we aim to address this issue by proposing an adversarial transfer learning based model ATLRec, which effectively captures domain-sharable features for cross-domain recommendation. In ATLRec, we leverage adversarial learning to generate representations of user-item interactions in both the source and the target domains, such that the discriminator cannot identify which domain they belong to, for the purpose of obtaining domain-sharable features. Meanwhile each domain learns its domain-specific features by a private feature extractor. The recommendation of each domain considers both domain-specific and domain-sharable features. We further adopt an attention mechanism to learn item latent factors of both domains by utilizing the shared users with interaction history, so that the representations of all items can be learned sufficiently in a shared space, even when few or even no items are shared by different domains. By this method, we can represent all items from the source and the target domains in a shared space, for the purpose of better linking items in different domains and capturing cross-domain item-item relatedness to facilitate the learning of domain-sharable knowledge. The proposed model is evaluated on various real-world datasets and demonstrated to outperform several state-of-the-art single-domain and cross-domain recommendation methods in terms of recommendation accuracy.