Log In Sign Up

Agent-based Graph Neural Networks

by   Karolis Martinkus, et al.

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 known graph neural networks. In AgentNet, some trained 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 3-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.


page 1

page 2

page 3

page 4


Graph Neural Networks with Precomputed Node Features

Most Graph Neural Networks (GNNs) cannot distinguish some graphs or inde...

A Hierarchy of Graph Neural Networks Based on Learnable Local Features

Graph neural networks (GNNs) are a powerful tool to learn representation...

Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network

Graph neural networks (GNNs) have achieved outstanding performance in le...

Classification on Large Networks: A Quantitative Bound via Motifs and Graphons

When each data point is a large graph, graph statistics such as densitie...

Explainability in subgraphs-enhanced Graph Neural Networks

Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been int...

Can graph neural networks count substructures?

The ability to detect and count certain substructures in graphs is impor...

Recognizing Spatial Configurations of Objects with Graph Neural Networks

Deep learning algorithms can be seen as compositions of functions acting...