Collaboration-Aware Graph Convolutional Network for Recommender Systems
This work addresses the need for more effective recommender systems by developing a novel GNN variant that enhances collaborative filtering, representing an incremental improvement over existing methods.
The paper tackles the problem of improving recommendation accuracy by analyzing how message-passing in GNNs captures collaborative effects, proposing a new metric (CIR) and a tailored GNN called CAGCN, which outperforms LightGCN by nearly 10% in Recall@20 and achieves around 80% speedup on six benchmark datasets.
Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative effect. Nevertheless, most of the existing message-passing mechanisms for recommendation are directly inherited from GNNs without scrutinizing whether the captured collaborative effect would benefit the prediction of user preferences. In this paper, we first analyze how message-passing captures the collaborative effect and propose a recommendation-oriented topological metric, Common Interacted Ratio (CIR), which measures the level of interaction between a specific neighbor of a node with the rest of its neighbors. After demonstrating the benefits of leveraging collaborations from neighbors with higher CIR, we propose a recommendation-tailored GNN, Collaboration-Aware Graph Convolutional Network (CAGCN), that goes beyond 1-Weisfeiler-Lehman(1-WL) test in distinguishing non-bipartite-subgraph-isomorphic graphs. Experiments on six benchmark datasets show that the best CAGCN variant outperforms the most representative GNN-based recommendation model, LightGCN, by nearly 10% in Recall@20 and also achieves around 80% speedup. Our code is publicly available at https://github.com/YuWVandy/CAGCN.