A Hierarchy of Graph Neural Networks Based on Learnable Local Features

by   Michael Lingzhi Li, et al.

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to compare different architectures and how to construct GNNs systematically. Here, we propose a hierarchy of GNNs based on their aggregation regions. We derive theoretical results about the discriminative power and feature representation capabilities of each class. Then, we show how this framework can be utilized to systematically construct arbitrarily powerful GNNs. As an example, we construct a simple architecture that exceeds the expressiveness of the Weisfeiler-Lehman graph isomorphism test. We empirically validate our theory on both synthetic and real-world benchmarks, and demonstrate our example's theoretical power translates to strong results on node classification, graph classification, and graph regression tasks.


page 1

page 2

page 3

page 4


How Powerful are Graph Neural Networks?

Graph Neural Networks (GNNs) for representation learning of graphs broad...

Principal Neighbourhood Aggregation for Graph Nets

Graph Neural Networks (GNNs) have been shown to be effective models for ...

Directional Graph Networks

In order to overcome the expressive limitations of graph neural networks...

Using Laplacian Spectrum as Graph Feature Representation

Graphs possess exotic features like variable size and absence of natural...

Motif Graph Neural Network

Graphs can model complicated interactions between entities, which natura...

Dissecting Graph Neural Networks on Graph Classification

Graph Neural Nets (GNNs) have received increasing attentions, partially ...

Agent-based Graph Neural Networks

We present a novel graph neural network we call AgentNet, which is desig...