Complete Neural Networks for Complete Euclidean Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hordan, Snir, Amir, Tal, Gortler, Steven J., Dym, Nadav
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911831450189824
author Hordan, Snir
Amir, Tal
Gortler, Steven J.
Dym, Nadav
author_facet Hordan, Snir
Amir, Tal
Gortler, Steven J.
Dym, Nadav
contents Neural networks for point clouds, which respect their natural invariance to permutation and rigid motion, have enjoyed recent success in modeling geometric phenomena, from molecular dynamics to recommender systems. Yet, to date, no model with polynomial complexity is known to be complete, that is, able to distinguish between any pair of non-isomorphic point clouds. We fill this theoretical gap by showing that point clouds can be completely determined, up to permutation and rigid motion, by applying the 3-WL graph isomorphism test to the point cloud's centralized Gram matrix. Moreover, we formulate an Euclidean variant of the 2-WL test and show that it is also sufficient to achieve completeness. We then show how our complete Euclidean WL tests can be simulated by an Euclidean graph neural network of moderate size and demonstrate their separation capability on highly symmetrical point clouds.
format Preprint
id arxiv_https___arxiv_org_abs_2301_13821
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Complete Neural Networks for Complete Euclidean Graphs
Hordan, Snir
Amir, Tal
Gortler, Steven J.
Dym, Nadav
Machine Learning
Neural networks for point clouds, which respect their natural invariance to permutation and rigid motion, have enjoyed recent success in modeling geometric phenomena, from molecular dynamics to recommender systems. Yet, to date, no model with polynomial complexity is known to be complete, that is, able to distinguish between any pair of non-isomorphic point clouds. We fill this theoretical gap by showing that point clouds can be completely determined, up to permutation and rigid motion, by applying the 3-WL graph isomorphism test to the point cloud's centralized Gram matrix. Moreover, we formulate an Euclidean variant of the 2-WL test and show that it is also sufficient to achieve completeness. We then show how our complete Euclidean WL tests can be simulated by an Euclidean graph neural network of moderate size and demonstrate their separation capability on highly symmetrical point clouds.
title Complete Neural Networks for Complete Euclidean Graphs
topic Machine Learning
url https://arxiv.org/abs/2301.13821