arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.01030cs.LG
收藏

图神经网络中基于Hamilton信息传播的节点嵌入

Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks

C3 AI(C3人工智能公司);Nanyang Technological University(南洋理工大学)

Qiyu Kang, Kai Zhao, Yang Song, Sijie Wang, Rui She, Wee Peng Tay

摘要:

图神经网络(GNN)在图结构数据的各种推理任务中取得了成功。然而,文献中许多GNN面临的共同挑战包括各种几何形状下的图节点嵌入问题和过平滑问题。为了解决这些问题,我们提出了一种新的图信息传播策略,称为Hamilton动态GNN(HDG),它使用Hamilton力学方法来学习图中的节点嵌入。HDG中的哈密顿能量函数是可学习的,并且可以适应任何给定图形数据集的底层几何。我们展示了HDG自动学习图形数据集的底层几何结构的能力,即使是那些具有复杂和混合几何结构的图形数据集,通过对各种下游任务的最先进基线进行全面评估。我们还验证了HDG对小扰动是稳定的,并且可以减轻堆叠许多层时的过度平滑问题。

英文摘要:

Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data. However, common challenges faced by many GNNs in the literature include the problem of graph node embedding under various geometries and the over-smoothing problem. To address these issues, we propose a novel graph information propagation strategy called Hamiltonian Dynamic GNN (HDG) that uses a Hamiltonian mechanics approach to learn node embeddings in a graph. The Hamiltonian energy function in HDG is learnable and can adapt to the underlying geometry of any given graph dataset. We demonstrate the ability of HDG to automatically learn the underlying geometry of graph datasets, even those with complex and mixed geometries, through comprehensive evaluations against state-of-the-art baselines on various downstream tasks. We also verify that HDG is stable against small perturbations and can mitigate the over-smoothing problem when stacking many layers.

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。

↑