Enumerating Unique Computational Graphs via an Iterative Graph Invariant

02/17/2019
by   Chris Ying, et al.
0

In this report, we describe a novel graph invariant for computational graphs (colored directed acylic graphs) and how we used it to generate all distinct computational graphs up to isomorphism for small graphs. The algorithm iteratively applies isomorphism-invariant operations, which take into account the graph structure and coloring, and outputs a fixed-length hash that is identical for all isomorphic computational graphs. While the algorithm cannot perfectly distinguish all pairs of non-isomorphic computational graphs, we suggest that it may be useful as a heuristic for comparing graphs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/05/2021

Graph Coloring: Comparing Cluster Graphs to Factor Graphs

We present a means of formulating and solving graph coloring problems wi...
research
11/21/2021

Isomorphism Testing for T-graphs in FPT

A T-graph (a special case of a chordal graph) is the intersection graph ...
research
10/17/2019

Graph Embedding VAE: A Permutation Invariant Model of Graph Structure

Generative models of graph structure have applications in biology and so...
research
08/14/2019

The Power of the Weisfeiler-Leman Algorithm to Decompose Graphs

The Weisfeiler-Leman procedure is a widely-used approach for graph isomo...
research
03/17/2023

On the Use of Geometric Deep Learning Towards the Evaluation of Graph-Centric Engineering Systems

Many complex engineering systems can be represented in a topological for...
research
01/22/2023

A graph isomorphism invariant based on neighborhood aggregation

This paper presents a new graph isomorphism invariant, called 𝔴-labeling...
research
05/03/2020

Graph Homomorphism Convolution

In this paper, we study the graph classification problem from the graph ...

Please sign up or login with your details

Forgot password? Click here to reset