Trainability for Universal GNNs Through Surgical Randomness

by   Billy Joe Franks, et al.

Message passing neural networks (MPNN) have provable limitations, which can be overcome by universal networks. However, universal networks are typically impractical. The only exception is random node initialization (RNI), a data augmentation method that results in provably universal networks. Unfortunately, RNI suffers from severe drawbacks such as slow convergence and high sensitivity to changes in hyperparameters. We transfer powerful techniques from the practical world of graph isomorphism testing to MPNNs, resolving these drawbacks. This culminates in individualization-refinement node initialization (IRNI). We replace the indiscriminate and haphazard randomness used in RNI by a surgical incision of only a few random bits at well-selected nodes. Our novel non-intrusive data-augmentation scheme maintains the networks' universality while resolving the trainability issues. We formally prove the claimed universality and corroborate experimentally – on synthetic benchmarks sets previously explicitly designed for that purpose – that IRNI overcomes the limitations of MPNNs. We also verify the practical efficacy of our approach on the standard benchmark data sets PROTEINS and NCI1.



There are no comments yet.


page 1

page 2

page 3

page 4


The Surprising Power of Graph Neural Networks with Random Node Initialization

Graph neural networks (GNNs) are effective models for representation lea...

SoftEdge: Regularizing Graph Classification with Random Soft Edges

Graph data augmentation plays a vital role in regularizing Graph Neural ...

Graph Representation Learning with Individualization and Refinement

Graph Neural Networks (GNNs) have emerged as prominent models for repres...

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

Most state-of-the-art Graph Neural Networks (GNNs) can be defined as a f...

A pipeline for fair comparison of graph neural networks in node classification tasks

Graph neural networks (GNNs) have been investigated for potential applic...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.