Accurate and Scalable Graph Convolutional Networks for Recommendation Based on Subgraph Propagation

In recommendation systems, Graph Convolutional Networks (GCNs) often suffer from significant computational and memory cost when propagating features across the entire user-item graph. While various sampling strategies have been introduced to reduce the cost, the challenge of neighbor explosion persists, primarily due to the iterative nature of neighbor aggregation. This work focuses on exploring subgraph propagation for scalable recommendation by addressing two primary challenges: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">efficient and effective subgraph construction</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">subgraph sparsity</i>. To address these challenges, we propose a novel <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GCN</u> model for recommendation based on <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sub</u>graph propagation, called SubGCN. One key component of SubGCN is BiPPR, a technique that fuses both source- and target-based Personalized PageRank (PPR) approximations, to overcome the challenge of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">efficient and effective subgraph construction</i>. Furthermore, we propose a source-target contrastive learning scheme to mitigate the impact of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">subgraph sparsity</i> for SubGCN. We conduct extensive experiments on two large and two medium-sized datasets to evaluate the scalability, efficiency, and effectiveness of SubGCN. On medium-sized datasets, compared to full-graph GCNs, SubGCN achieves competitive accuracy while using only 23.79% training time on Gowalla and 16.3% on Yelp2018. On large datasets, where full-graph GCNs ran out of the GPU memory, our proposed SubGCN outperforms widely used sampling strategies in terms of training efficiency and recommendation accuracy.