RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems
RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems
复制标题
DOI：
10.1109/tnnls.2019.2907430
复制
发表时间：
2019-03
影响因子：
10.4
通讯作者：
Cheng Wang;Hui Li;Mathias Niepert;Hui Li
中科院分区：
文献类型：
--
作者：
Cheng Wang;Hui Li;Mathias Niepert;Hui Li
数据稀疏性和数据不平衡性是跨域推荐系统中的一个实际问题。本文通过利用来自表示学习、对抗学习和迁移学习（特别是领域适应）的概念来解决这些问题。虽然各种迁移学习方法在这种情况下表现出了良好的性能，但我们提出的新方法RecSys-DAN专注于减轻跨域和域内数据稀疏性和数据不平衡，并学习用户，项目及其交互的可转移潜在表示。与现有方法不同，该方法以对抗的方式将潜在表征从源域转移到目标域。目标域中的映射函数通过玩具有对抗性损失的最小-最大博弈来学习，旨在为一个子空间生成域不可区分的表示。提出并探索了ResSys-DAN的四个神经架构实例。对现实世界亚马逊数据的实证结果表明，即使不使用标记数据（即，在目标域中，与最先进的监督方法相比，RecSys-DAN实现了具有竞争力的性能。更重要的是，RecSys-DAN对单模态和多模态场景都具有高度灵活性，因此它对冷启动建议更具鲁棒性，这是以前方法难以实现的。
Data sparsity and data imbalance are practical and challenging issues in cross-domain recommender systems (RSs). 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 the 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 the previous methods.