Graph Neural Networks (GNNs) have recently been applied to graph learning tasks and achieved state-of-the-art (SOTA) results. However, many competitive methods run GNNs multiple times with subgraph extraction and customized labeling to capture information that is hard for normal GNNs to learn. Such operations are time-consuming and do not scale to large graphs. In this paper, we propose an efficient GNN framework called Geodesic GNN (GDGNN) that requires only one GNN run and injects conditional relationships between nodes into the model without labeling. This strategy effectively reduces the runtime of subgraph methods. Specifically, we view the shortest paths between two nodes as the spatial graph context of the neighborhood around them. The GNN embeddings of nodes on the shortest paths are used to generate geodesic representations. Conditioned on the geodesic representations, GDGNN can generate node, link, and graph representations that carry much richer structural information than plain GNNs. We theoretically prove that GDGNN is more powerful than plain GNNs. We present experimental results to show that GDGNN achieves highly competitive performance with SOTA GNN models on various graph learning tasks while taking significantly less time.
Graph Generation with Spectral Geodesic Flow Matching
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学科学国家重点实验室,数学与系统科学研究院,中国科学院);School of Mathematics Sciences, University of Chinese Academy of Sciences(中国科学院大学数学科学学院);Key Laboratory of Systems Health Science of Zhejiang Province, School of Life Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences(浙江省系统健康科学重点实验室,生命科学学院,杭州高等研究院,中国科学院)
Learning Relativistic Geodesics and Chaotic Dynamics via Stabilized Lagrangian Neural Networks
Department of Physics, Bogazici University, Istanbul, Turkey(物理系,博兹达奇大学,伊斯坦布尔,土耳其);Department of Computer Engineering, Bogazici University, Istanbul, Turkey(计算机工程系,博兹达奇大学,伊斯坦布尔,土耳其)
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学);School of Mathematics and Statistics, Fujian Normal University(福建师范大学数学与统计学学院);Beijing Institute of Technology(北京理工大学)
Hamiltonian Neural Networks approach to fuzzball geodesics
GSI Helmholtz Centre for Heavy Ion Research(重离子研究中心GSI);School of Fundamental Physics and Mathematical Sciences(基础物理与数学科学学院);Hangzhou Institute for Advanced Study, UCAS(杭州高等研究 institute)
Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity
Wharton School, University of Pennsylvania(宾夕法尼亚大学沃顿商学院);Peking University(北京大学);Stanford University(斯坦福大学);School of Mathematical Sciences, Peking University(北京大学数学科学学院);Center for Machine Learning Research, Peking University(北京大学机器学习研究中心)