Attention on Global-Local Representation Spaces in Recommender Systems
This is an incremental improvement for recommender systems, addressing data sparsity and scalability by better modeling user-item interactions.
The paper tackles the problem of characterizing complex user-item interactions in recommender systems by proposing a clustering-based collaborative filtering method that uses multiple representation spaces, and it shows superior performance over single-space methods on four benchmark datasets.
In this study, we present a novel clustering-based collaborative filtering (CF) method for recommender systems. Clustering-based CF methods can effectively deal with data sparsity and scalability problems. However, most of them are applied to a single representation space, which might not characterize complex user-item interactions well. We argue that the user-item interactions should be observed from multiple views and characterized in an adaptive way. To address this issue, we leveraged the global and local properties to construct multiple representation spaces by learning various training datasets and loss functions. An attention network was built to generate a blended representation according to the relative importance of the representation spaces for each user-item pair, providing a flexible way to characterize diverse user-item interactions. Substantial experiments were evaluated on four popular benchmark datasets. The results show that the proposed method is superior to several CF methods where only one representation space is considered.