跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26384 · v1

A Complete Geometric Message-Passing Architecture for Point Clouds

面向点云的完备几何消息传递架构

首次提交 2026-11-20 00:40
版本更新 2026-11-20 00:40
雷达观测 2026-11-20 12:52
arXiv ↗PDF ↗

摘要

Three-dimensional point clouds are a fundamental data modality, and a large family of machine learning architectures has been developed to respect their natural symmetries to rigid motions and permutations. A principled way to compare these architectures, which vary widely in complexity and cost, is through their expressive power. That is, an architecture is complete if it can distinguish any two inputs not related by the symmetries it respects. Simple distance-based message-passing networks are known to be incomplete, and while there exist complete alternatives, they typically rely on computationally intensive mechanisms like high-order representations of the rotation group or higher-order Weisfeiler-Leman-type tests. In this work, we devise a novel, simple, equivariant message-passing architecture for point clouds, and prove that it is complete. We complement our theoretical result with experiments showing that our architecture separates challenging point clouds that distance-based message passing provably cannot distinguish. Our results suggest that high-order equivariant features may not be necessary to enhance the expressivity of point cloud architectures, and can help settle completeness for other equivariant architectures for which such results are currently unknown. We give initial evidence for this by proving completeness of a slightly modified version of SEGNN.

作者备注:44 pages, 4 figures, 4 tables. Ancillary files: exact-arithmetic verifier, certificate and companion notebook for the Platonic color-atom computation

AI 论文解读

基于摘要 · 非全文审阅

提出一种简单且等变的点云消息传递架构,并证明其具有完备性,实验表明它能区分基于距离的消息传递无法区分的点云。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-20 00:40 · 最新观测版本

A Complete Geometric Message-Passing Architecture for Point Clouds

Three-dimensional point clouds are a fundamental data modality, and a large family of machine learning architectures has been developed to respect their natural symmetries to rigid motions and permutations. A principled way to compare these architectures, which vary widely in complexity and cost, is through their expressive power. That is, an architecture is complete if it can distinguish any two inputs not related by the symmetries it respects. Simple distance-based message-passing networks are known to be incomplete, and while there exist complete alternatives, they typically rely on computationally intensive mechanisms like high-order representations of the rotation group or higher-order Weisfeiler-Leman-type tests. In this work, we devise a novel, simple, equivariant message-passing architecture for point clouds, and prove that it is complete. We complement our theoretical result with experiments showing that our architecture separates challenging point clouds that distance-based message passing provably cannot distinguish. Our results suggest that high-order equivariant features may not be necessary to enhance the expressivity of point cloud architectures, and can help settle completeness for other equivariant architectures for which such results are currently unknown. We give initial evidence for this by proving completeness of a slightly modified version of SEGNN.

查看此版本解读 →查看此版本原文 ↗