DeepAI AI Chat
Log In Sign Up

On Graph Neural Networks versus Graph-Augmented MLPs

by   Lei Chen, et al.

From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments node features with certain multi-hop operators on the graph and then applies an MLP in a node-wise fashion. From the perspective of graph isomorphism testing, we show both theoretically and numerically that GA-MLPs with suitable operators can distinguish almost all non-isomorphic graphs, just like the Weifeiler-Lehman (WL) test. However, by viewing them as node-level functions and examining the equivalence classes they induce on rooted graphs, we prove a separation in expressive power between GA-MLPs and GNNs that grows exponentially in depth. In particular, unlike GNNs, GA-MLPs are unable to count the number of attributed walks. We also demonstrate via community detection experiments that GA-MLPs can be limited by their choice of operator family, as compared to GNNs with higher flexibility in learning.


page 1

page 2

page 3

page 4


Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

While graph kernels (GKs) are easy to train and enjoy provable theoretic...

Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework

The Graph Augmented Multi-layer Perceptron (GA-MLP) model is an attracti...

On the equivalence between graph isomorphism testing and function approximation with GNNs

Graph neural networks (GNNs) have achieved lots of success on graph-stru...

Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels

Graph neural networks (GNNs) have achieved tremendous success in graph m...

Incidence Networks for Geometric Deep Learning

One may represent a graph using both its node-edge and its node-node inc...

A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks

In recent years, graph neural networks (GNNs) have gained increasing att...