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 2407.00696cs.LG
收藏

图在图神经网络中

Graph in Graph Neural Network

School of Computing and Mathematical Sciences, University of Leicester(莱斯特大学计算与数学科学学院);University of Cambridge(剑桥大学);Department of Computing, Imperial College London(帝国理工学院计算系)

Jiongshu Wang, Jing Yang, Jiankang Deng, Hatice Gunes, Siyang Song

AI总结:

本文提出图在图神经网络(GIG),首次使GNN能处理顶点本身为图的样本,通过顶点级和全局级更新利用图内线索与图间关系,在13/14个数据集上取得最先进结果。

摘要:

现有的图神经网络(GNN)仅限于处理每个顶点由向量或单个值表示的图,这限制了它们描述复杂对象的表示能力。在本文中,我们提出了第一个能够处理图风格数据(称为GIG样本)的GNN(称为图在图神经网络(GIG)网络),其中GIG样本的顶点进一步由图表示。给定一组图或一个其组成部分可以由一组图表示的数据样本(称为多图数据样本),我们的GIG网络首先使用一个GIG样本生成(GSG)模块,将输入编码为一个GIG样本,其中每个GIG顶点包含一个图。然后,堆叠一组GIG隐藏层,每个隐藏层包括:(1)一个GIG顶点级更新(GVU)模块,该模块基于每个GIG顶点内部信息单独更新该顶点中的图;以及(2)一个全局级GIG样本更新(GGU)模块,该模块基于所有GIG顶点之间的关系更新这些顶点中的图,使更新后的GIG顶点具有全局上下文感知能力。通过这种方式,每个GIG顶点所包含图的内部线索以及GIG顶点之间的关系都可以用于下游任务。实验结果表明,我们的GIG网络不仅在各种通用图分析任务上具有良好的泛化能力,而且在现实世界的多图数据分析(例如,基于人体骨架视频的动作识别)上也表现良好,在14个评估数据集中的13个上取得了新的最先进结果。我们的代码已在https://github.com/wangjs96/Graph-in-Graph-Neural-Network上公开可用。

英文摘要:

Existing Graph Neural Networks (GNNs) are limited to process graphs each of whose vertices is represented by a vector or a single value, limited their representing capability to describe complex objects. In this paper, we propose the first GNN (called Graph in Graph Neural (GIG) Network) which can process graph-style data (called GIG sample) whose vertices are further represented by graphs. Given a set of graphs or a data sample whose components can be represented by a set of graphs (called multi-graph data sample), our GIG network starts with a GIG sample generation (GSG) module which encodes the input as a \textbf{GIG sample}, where each GIG vertex includes a graph. Then, a set of GIG hidden layers are stacked, with each consisting of: (1) a GIG vertex-level updating (GVU) module that individually updates the graph in every GIG vertex based on its internal information; and (2) a global-level GIG sample updating (GGU) module that updates graphs in all GIG vertices based on their relationships, making the updated GIG vertices become global context-aware. This way, both internal cues within the graph contained in each GIG vertex and the relationships among GIG vertices could be utilized for down-stream tasks. Experimental results demonstrate that our GIG network generalizes well for not only various generic graph analysis tasks but also real-world multi-graph data analysis (e.g., human skeleton video-based action recognition), which achieved the new state-of-the-art results on 13 out of 14 evaluated datasets. Our code is publicly available at https://github.com/wangjs96/Graph-in-Graph-Neural-Network.

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。

↑