Knowledge transfer learning from multiple user activities to improve personalized recommendation

Representation learning has attracted growing attention in recommendation system. In addition, deep learning has been adopted to build a representation generator based on content data (e.g., reviews, descriptions), and has been verified to be an excellent method for recommendation system. However, the content data may not be sufficient to capture the hidden features of user behavior patterns. We argue that the underlying information in behavior patterns can characterize users, by generating specific representation from user activities. In this paper, we propose a deep transfer learning-based recommendation model (DeepTransferR), which conducts knowledge transfer from multiple user activities. We adopt attention network to migrate the behavior pattern from auxiliary activities, and to generate personalized representations for users. In DeepTransferR, we set up an independent predictor for each user activity. We then define a weighted loss function to model knowledge interaction by incorporating the independent loss in each activity predictor. Experiments have been conducted on real-world datasets, and the results show that the proposed model outperforms the state-of-the-art methods in not only recommendation performance, but also convergence and robustness in sparse-data and cold-start environments.