Using Laplacian Spectrum as Graph Feature Representation

12/02/2019
by   Edouard Pineau, et al.
0

Graphs possess exotic features like variable size and absence of natural ordering of the nodes that make them difficult to analyze and compare. To circumvent this problem and learn on graphs, graph feature representation is required. A good graph representation must satisfy the preservation of structural information, with two particular key attributes: consistency under deformation and invariance under isomorphism. While state-of-the-art methods seek such properties with powerful graph neural-networks, we propose to leverage a simple graph feature: the graph Laplacian spectrum (GLS). We first remind and show that GLS satisfies the aforementioned key attributes, using a graph perturbation approach. In particular, we derive bounds for the distance between two GLS that are related to the divergence to isomorphism, a standard computationally expensive graph divergence. We finally experiment GLS as graph representation through consistency tests and classification tasks, and show that it is a strong graph feature representation baseline.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/13/2019

A Hierarchy of Graph Neural Networks Based on Learnable Local Features

Graph neural networks (GNNs) are a powerful tool to learn representation...
research
10/14/2021

sMGC: A Complex-Valued Graph Convolutional Network via Magnetic Laplacian for Directed Graphs

Recent advancements in Graph Neural Networks have led to state-of-the-ar...
research
07/31/2017

Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning

One question central to Reinforcement Learning is how to learn a feature...
research
02/01/2022

Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction

We consider feature representation learning problem of molecular graphs....
research
05/30/2018

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications

The von Neumann graph entropy (VNGE) facilitates the measure of informat...
research
10/22/2021

Signature-Graph Networks

We propose a novel approach for visual representation learning called Si...

Please sign up or login with your details

Forgot password? Click here to reset