DeepAI
Log In Sign Up

Graph Neural Networks with Local Graph Parameters

06/12/2021
by   Pablo Barceló, et al.
0

Various recent proposals increase the distinguishing power of Graph Neural Networks GNNs by propagating features between k-tuples of vertices. The distinguishing power of these "higher-order” GNNs is known to be bounded by the k-dimensional Weisfeiler-Leman (WL) test, yet their 𝒪(n^k) memory requirements limit their applicability. Other proposals infuse GNNs with local higher-order graph structural information from the start, hereby inheriting the desirable 𝒪(n) memory requirement from GNNs at the cost of a one-time, possibly non-linear, preprocessing step. We propose local graph parameter enabled GNNs as a framework for studying the latter kind of approaches and precisely characterize their distinguishing power, in terms of a variant of the WL test, and in terms of the graph structural properties that they can take into account. Local graph parameters can be added to any GNN architecture, and are cheap to compute. In terms of expressive power, our proposal lies in the middle of GNNs and their higher-order counterparts. Further, we propose several techniques to aide in choosing the right local graph parameters. Our results connect GNNs with deep results in finite model theory and finite variable logics. Our experimental evaluation shows that adding local graph parameters often has a positive effect for a variety of GNNs, datasets and graph learning tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/04/2018

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

In recent years, graph neural networks (GNNs) have emerged as a powerful...
01/30/2022

A Theoretical Comparison of Graph Neural Network Extensions

We study and compare different Graph Neural Network extensions that incr...
10/02/2020

The Surprising Power of Graph Neural Networks with Random Node Initialization

Graph neural networks (GNNs) are effective models for representation lea...
12/06/2020

Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results

While massage passing based Graph Neural Networks (GNNs) have become inc...
04/10/2022

Expressiveness and Approximation Properties of Graph Neural Networks

Characterizing the separation power of graph neural networks (GNNs) prov...
01/27/2022

A Higher-Order Semantic Dependency Parser

Higher-order features bring significant accuracy gains in semantic depen...
04/02/2019

Towards a practical k-dimensional Weisfeiler-Leman algorithm

The k-dimensional Weisfeiler-Leman algorithm is a well-known heuristic f...