arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.06316cs.LGstat.ML
收藏

等距变换不变与等变图卷积网络

Isometric Transformation Invariant and Equivariant Graph Convolutional Networks

University of Tsukuba(筑波大学);Research Institute for Computational Science Co. Ltd.(计算科学研究所有限公司)

Masanobu Horie, Naoki Morita, Toshiaki Hishinuma, Yu Ihara, Naoto Mitsume

摘要:

图是表示对象间成对关系的最重要的数据结构之一。具体来说,嵌入在欧几里得空间中的图对于解决实际问题(如物理模拟)至关重要。将欧几里得空间中的图应用于物理模拟的关键要求是以计算高效的方式学习和推断等距变换不变和等变特征。在本文中,我们提出了一套基于图卷积网络的变换不变和等变模型,称为IsoGCN。我们证明,该模型具有竞争力的性能相比,国家的最先进的方法有关的几何和物理仿真数据的任务。此外,该模型可以扩展到1M顶点的图,并进行推理速度比传统的有限元分析,现有的等变模型无法实现。

英文摘要:

Graphs are one of the most important data structures for representing pairwise relations between objects. Specifically, a graph embedded in a Euclidean space is essential to solving real problems, such as physical simulations. A crucial requirement for applying graphs in Euclidean spaces to physical simulations is learning and inferring the isometric transformation invariant and equivariant features in a computationally efficient manner. In this paper, we propose a set of transformation invariant and equivariant models based on graph convolutional networks, called IsoGCNs. We demonstrate that the proposed model has a competitive performance compared to state-of-the-art methods on tasks related to geometrical and physical simulation data. Moreover, the proposed model can scale up to graphs with 1M vertices and conduct an inference faster than a conventional finite element analysis, which the existing equivariant models cannot achieve.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑