Hierarchical Bipartite Graph Convolutional Network for Recommendation

Graph Neural Networks (GNNs) have emerged as a dominant paradigm in machine learning for graphs, and recently developed Recommendation System (RecSys) models have significantly benefited from them. However, recent research has highlighted a limitation in classical GNNs, revealing that their message-passing mechanism is inherently flat, making it unable to capture hierarchical semantics within the graph. Recognizing the potential richness of information in the hierarchical structure of user-item bipartite graphs for RecSys, this paper introduces a novel end-to-end GNN-based RecSys model called Hierarchical Bipartite Graph Convolutional Network (HierBGCN). Specifically, we devise a BiDiffPool layer capable of performing differentiable pooling operations on the bipartite graph while preserving crucial properties. Through the stacking of multiple BiDiffPool layers, the bipartite graph undergoes hierarchical coarsening, enabling the extraction of multi-level knowledge. This allows GNNs to operate at each level, capturing diverse, high-order user-item interactions. Ultimately, the information from each coarsening level is aggregated to generate final user/item representations, effectively encapsulating the hierarchical knowledge inherent in user-item interactions. Empirical experiments conducted on four established RecSys datasets consistently demonstrate the superior performance of the proposed HierBGCN compared to competing models.