AI RESEARCH
S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
arXiv CS.LG
•
ArXi:2605.23467v1 Announce Type: new Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing (OSQ) phenomenon. Alongside spatial connectivity enrichment (e.g., rewiring), recent studies have shown that spectral filtering can yield strong long-range learning outcomes, as spectral operators enable global information mixing that alleviates