Abstract
User and item representation learning is critical for recommendation. Many of existing recommendation methods learn representations of users and items based on their ratings and reviews. However, the user-user and item-item relatedness are usually not considered in these methods, which may be insufficient. In this paper, we propose a neural recommendation approach which can utilize useful information from both review content and user-item graphs. Since reviews and graphs have different characteristics, we propose to use a multi-view learning framework to incorporate them as different views. In the review content-view, we propose to use a hierarchical model to first learn sentence representations from words, then learn review representations from sentences, and finally learn user/item representations from reviews. In addition, we propose to incorporate a three-level attention network into this view to select important words, sentences and reviews for learning informative user and item representations. In the graph-view, we propose a hierarchical graph neural network to jointly model the user-item, user-user and item-item relatedness by capturing the first- and second-order interactions between users and items in the user-item graph. In addition, we apply attention mechanism to model the importance of these interactions to learn informative user and item representations. Extensive experiments on four benchmark datasets validate the effectiveness of our approach.
Highlights
Learning user and item representations is critical for recommendation (Tay et al, 2018)
We propose to incorporate attention mechanism into the graph neural network to model the importance of these interactions for informative user and item representation learning
Chen et al (2018) proposed to learn review representations using convolutional neural networks (CNN) and they modeled the usefulness of reviews via a review-level attention network to learn informative user and item representation learning
Summary
Learning user and item representations is critical for recommendation (Tay et al, 2018). Zheng et al (2017) proposed a DeepCoNN approach to learn the representations of users and items from their reviews via convolutional neural networks (CNN). These methods only consider the interactions of user-item pairs, while the relatedness between users or items are ignored, which may be insufficient for learning accurate user and item representations. We propose to apply a three-level attention network to select important words, sentences and reviews to learn informative user and item representations. We propose to incorporate attention mechanism into the graph neural network to model the importance of these interactions for informative user and item representation learning. Extensive experiments on four benchmark datasets validate that our approach can effectively improve the performance of recommendation and outperform many baseline methods
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have