Fast and Deep Graph Neural Networks

TL;DR

This paper introduces a highly efficient deep graph neural network architecture that leverages fixed points of dynamical systems and sparse, untrained recurrent units to achieve competitive or superior performance in graph classification tasks.

Contribution

It proposes a novel deep GNN framework using fixed points and untrained sparse recurrent units, providing efficiency and insights into architecture power without extensive training.

Findings

Achieves state-of-the-art performance without training recurrent weights.

Uses small, sparse networks for efficiency and simplicity.

Demonstrates the architecture's effectiveness on graph classification tasks.

Abstract

We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural network), and leverages a deep architectural organization of the recurrent units. Efficiency is gained by many aspects, including the use of small and very sparse networks, where the weights of the recurrent units are left untrained under the stability condition introduced in this work. This can be viewed as a way to study the intrinsic power of the architecture of a deep GNN, and also to provide insights for the set-up of more complex fully-trained models. Through experimental results, we show that even without training of the recurrent connections, the architecture of small deep GNN is surprisingly able to achieve or improve the state-of-the-art performance on a significant set of tasks in the field of graphs classification.