论文标题
部分可观测时空混沌系统的无模型预测
Agent-based Graph Neural Networks
论文作者
论文摘要
我们提出了一个新的图形神经网络，我们称为AgentNet，该网络专为图形级任务而设计。 AgentNet的灵感来自子宫性算法，其计算复杂性与图形大小无关。代理Net的体系结构从根本上不同于传统图神经网络的体系结构。在AgentNet中，一些受过训练的\ textit {neural Agents}智能地行走图，然后共同决定输出。我们提供了对AgentNet的广泛理论分析：我们表明，代理可以学会系统地探索他们的邻居，并且AgentNet可以区分某些甚至由2-WL无法区分的结构。此外，AgentNet能够将任何两个图表分开，这些图在子图方面完全不同。我们通过在难以辨认的图表和现实图形分类任务上进行合成实验来确认这些理论结果。在这两种情况下，我们都不仅与标准GNN相比，而且与计算更昂贵的GNN扩展相比。
We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computational complexity that is independent of the graph size. The architecture of AgentNet differs fundamentally from the architectures of traditional graph neural networks. In AgentNet, some trained \textit{neural agents} intelligently walk the graph, and then collectively decide on the output. We provide an extensive theoretical analysis of AgentNet: We show that the agents can learn to systematically explore their neighborhood and that AgentNet can distinguish some structures that are even indistinguishable by 2-WL. Moreover, AgentNet is able to separate any two graphs which are sufficiently different in terms of subgraphs. We confirm these theoretical results with synthetic experiments on hard-to-distinguish graphs and real-world graph classification tasks. In both cases, we compare favorably not only to standard GNNs but also to computationally more expensive GNN extensions.
