面向点云的完备几何消息传递架构
A Complete Geometric Message-Passing Architecture for Point Clouds
Nadav Dym, Tal Amir, Gia Chi Dang, Christopher Morris
AI 速读 基于摘要
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。
cs.LG
查看原文摘要
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.