arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.16092cs.LG
收藏

特征传输改进图神经网络

Feature Transportation Improves Graph Neural Networks

Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Moshe Eliasof, Eldad Haber, Eran Treister

AI总结:

本文提出受对流-扩散-反应系统启发的ADR-GNN架构,结合特征传输、局部平滑与非线性变换,在节点分类和时空任务上达到或超越最先进性能。

摘要:

图神经网络(GNNs)在表示图结构数据的学习中已显示出显著的成功。然而,GNNs在建模涉及特征传输的复杂现象时仍面临挑战。本文提出了一种受对流-扩散-反应系统启发的新型GNN架构,称为ADR-GNN。对流模拟特征传输,扩散捕捉特征的局部平滑,反应则代表特征通道之间的非线性变换。我们提供了对ADR-GNN定性行为的分析,展示了结合对流、扩散和反应的优势。为了证明其有效性,我们在真实世界的节点分类和时空数据集上评估了ADR-GNN,并表明其相比最先进的网络实现了改进或具有竞争力的性能。

英文摘要:

Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena that involve feature transportation. In this paper, we propose a novel GNN architecture inspired by Advection-Diffusion-Reaction systems, called ADR-GNN. Advection models feature transportation, while diffusion captures the local smoothing of features, and reaction represents the non-linear transformation between feature channels. We provide an analysis of the qualitative behavior of ADR-GNN, that shows the benefit of combining advection, diffusion, and reaction. To demonstrate its efficacy, we evaluate ADR-GNN on real-world node classification and spatio-temporal datasets, and show that it improves or offers competitive performance compared to state-of-the-art networks.

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。

↑