Attention-Based Recommendation On Graphs
This work addresses the problem of enhancing recommendation systems for users by integrating attention mechanisms with GCNs, representing an incremental improvement over existing graph neural network methods.
The authors tackled the problem of improving recommendation accuracy in collaborative filtering by proposing GARec, a model-based recommender system that uses an attention mechanism with a spatial Graph Convolutional Network (GCN) on a graph to extract embeddings for users and items, resulting in outperformance over baseline algorithms in terms of RMSE on MovieLens datasets.
Graph Neural Networks (GNN) have shown remarkable performance in different tasks. However, there are a few studies about GNN on recommender systems. GCN as a type of GNNs can extract high-quality embeddings for different entities in a graph. In a collaborative filtering task, the core problem is to find out how informative an entity would be for predicting the future behavior of a target user. Using an attention mechanism, we can enable GCNs to do such an analysis when the underlying data is modeled as a graph. In this study, we proposed GARec as a model-based recommender system that applies an attention mechanism along with a spatial GCN on a recommender graph to extract embeddings for users and items. The attention mechanism tells GCN how much a related user or item should affect the final representation of the target entity. We compared the performance of GARec against some baseline algorithms in terms of RMSE. The presented method outperforms existing model-based, non-graph neural networks and graph neural networks in different MovieLens datasets.