ResearchTrend.AI
  • Papers
  • Communities
  • Organizations
  • Events
  • Blog
  • Pricing
  • Feedback
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2303.12853
80
8
v1v2v3v4 (latest)

Three iterations of (d−1)(d-1)(d−1)-WL test distinguish non isometric clouds of ddd-dimensional points

22 March 2023
Valentino Delle Rose
Alexander Kozachinskiy
Cristóbal Rojas
Mircea Petrache
Pablo Barceló
ArXiv (abs)PDFHTML
Main:19 Pages
2 Figures
Bibliography:2 Pages
Abstract

The Weisfeiler--Lehman (WL) test is a fundamental iterative algorithm for checking isomorphism of graphs. It has also been observed that it underlies the design of several graph neural network architectures, whose capabilities and performance can be understood in terms of the expressive power of this test. Motivated by recent developments in machine learning applications to datasets involving three-dimensional objects, we study when the WL test is {\em complete} for clouds of euclidean points represented by complete distance graphs, i.e., when it can distinguish, up to isometry, any arbitrary such cloud. Our main result states that the (d−1)(d-1)(d−1)-dimensional WL test is complete for point clouds in ddd-dimensional Euclidean space, for any d≥2d\ge 2d≥2, and that only three iterations of the test suffice. Our result is tight for d=2,3d = 2, 3d=2,3. We also observe that the ddd-dimensional WL test only requires one iteration to achieve completeness.

View on arXiv
Comments on this paper