Search

Existing recommendation methods mainly learn user preference from historical user-item interaction data, while ignoring the extent of interactions, i.e., diverse user experience and user intention. To be more specific, for new users with little or no experience, they may turn to popular items preferred by majority users. In terms of those medium-level users who already have interacted with some items, they may require and expect items to meet their personal preferences. As pro-active users are likely to leave rich behavior (action) feedback (e.g., view, like) on the items they interacted with, the system will have good chance to better interpret users' intention, and thus generate more accurate and elaborate recommendations to hit their preferences. In this paper, we propose a generic M ulti-facet U ser P reference L earning (MUPL) framework for fine-grained item recommendation. By considering diverse user experience and intention, MUPL captures user preference in the level of group-, individual- and action-facet. Besides, the importance of user preference in different facets can be automatically learnt by MUPL. Extensive experiments on two real-world datasets (Xing, Sobazaar) demonstrate the superiority of our proposed approach over other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recommender systems aim to suggest items of interest from historical interactions between users and items. Advanced methods such as path-based recommendations attempt to capture high-order user–item interactions for better recommendation performance. However, these methods focus more on the local view of user–item interactions, ignoring the global view, which limits performance. Two more drawbacks further restrict the performance of existing methods. First, most do not consider the relations (or relation directions) between successive nodes when constructing a multi-hop path (i.e., high-order local interactions) from a user to a target item. Second, the influential factors of path length and number of relation types are ignored when computing path importance to aggregate paths for better local representation. To resolve these issues, we propose a recommendation model that can well capture high-order local and global (HOLG) user–item interactions. A path-embedding module learns a local representation of user–item interactions via a long short-term memory network, taking (directed) relations of successive nodes as input. Multiple local representations are aggregated with an attention network, using both path length and number of relation types as important factors. A graph-embedding module learns a global representation of user–item interactions by constructing a subgraph from sampled user–item paths. Experiments on the LinkedIn, MovieLens-1M, and Yelp datasets validate our approach, which performs best in comparison with eight baselines. [ABSTRACT FROM AUTHOR]

Recently, Generative Adversarial Networks (GANs) have received much attention in recommender systems because they can capture complex data distributions. They rely on two sub-networks, generator and discriminator models, to generate 'fake' yet reliable data, so better recommendation accuracy can be obtained. However, most variants of existing GANs achieve accuracy improvements by greatly increasing the model complexity, especially the amount of parameters, leading to difficulty in the deployment of those methods. Therefore, we aim to resolve this issue by learning compact yet accurate GANs that can make up valuable data with less generator parameters. To this end, we integrate knowledge distillation (KD, in the form of a teacher–student architecture) into GANs to reduce the model complexity while improving the accuracy of GANs. To the best of our knowledge, this work is the first to learn compact GANs for recommender systems by applying a KD framework named StuGAN. Specifically, we use a student discriminator to refine the teacher's knowledge, and then both the generator and discriminator are enhanced by leveraging the refined knowledge via adversarial learning, which constrains the generator to produce fake data approximating both the ground truth and teacher's predicted preferences, and enables the discriminator to distinguish between the preferences of the generator and more confusing preferences of the teacher from the ground truth. Finally, we conduct extensive experiments on two real-world datasets (i.e., Ciao and LastFM), and the results show that our approach can reduce the volume of model parameters by as much as half while maintaining comparable recommendation accuracy. [ABSTRACT FROM AUTHOR]