Beltrami Flow and Neural Diffusion on Graphs
Twitter Inc.（Twitter公司）；University of Oxford（牛津大学）；Imperial College London（帝国理工学院）
英文摘要：
We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positional encodings derived from the graph topology and jointly evolved by the Beltrami flow, producing simultaneously continuous feature learning and topology evolution. The resulting model generalises many popular graph neural networks and achieves state-of-the-art results on several benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
