Fast and Deep Graph Neural Networks

11/20/2019
by   Claudio Gallicchio, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/02/2020

Architectural Implications of Graph Neural Networks

Graph neural networks (GNN) represent an emerging line of deep learning ...
research
03/20/2022

Differentiable Reasoning over Long Stories – Assessing Systematic Generalisation in Neural Models

Contemporary neural networks have achieved a series of developments and ...
research
02/28/2022

RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation

Network modeling is a fundamental tool in network research, design, and ...
research
02/16/2021

ReGraphX: NoC-enabled 3D Heterogeneous ReRAM Architecture for Training Graph Neural Networks

Graph Neural Network (GNN) is a variant of Deep Neural Networks (DNNs) o...
research
10/29/2018

Mean-field theory of graph neural networks in graph partitioning

A theoretical performance analysis of the graph neural network (GNN) is ...
research
11/14/2020

Discovery of the Hidden State in Ionic Models Using a Domain-Specific Recurrent Neural Network

Ionic models, the set of ordinary differential equations (ODEs) describi...
research
09/17/2018

Graph Neural Networks for IceCube Signal Classification

Tasks involving the analysis of geometric (graph- and manifold-structure...

Please sign up or login with your details

Forgot password? Click here to reset