Agent-based Graph Neural Networks
Karolis Martinkus, Pál András Papp, Benedikt Schesch, Roger Wattenhofer
Abstract
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.
BibTeX
@inproceedings{
martinkus2023agentbased,
title={Agent-based Graph Neural Networks},
author={Karolis Martinkus and P{\'a}l Andr{\'a}s Papp and Benedikt Schesch and Roger Wattenhofer},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=8WTAh0tj2jC}
}