Agent-based Graph Neural Networks. (arXiv:2206.11010v1 [cs.LG])

Web: http://arxiv.org/abs/2206.11010

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
\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 …

arxiv graph graph neural networks lg networks neural neural networks