Next Level Message-Passing with Hierarchical Support Graphs
This addresses a known bottleneck in graph learning for researchers and practitioners, though it builds incrementally on existing virtual node approaches.
The paper tackles the limited information exchange in Message-Passing Neural Networks (MPNNs) by introducing Hierarchical Support Graphs (HSGs), which recursively coarsen graphs to enhance information flow, achieving state-of-the-art results across multiple datasets.
Message-Passing Neural Networks (MPNNs) are extensively employed in graph learning tasks but suffer from limitations such as the restricted scope of information exchange, by being confined to neighboring nodes during each round of message passing. Various strategies have been proposed to address these limitations, including incorporating virtual nodes to facilitate global information exchange. In this study, we introduce the Hierarchical Support Graph (HSG), an extension of the virtual node concept created through recursive coarsening of the original graph. This approach provides a flexible framework for enhancing information flow in graphs, independent of the specific MPNN layers utilized. We present a theoretical analysis of HSGs, investigate their empirical performance, and demonstrate that HSGs can surpass other methods augmented with virtual nodes, achieving state-of-the-art results across multiple datasets.