arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.09844cs.LGstat.ML
收藏

E(n)等变图神经网络

E(n) Equivariant Graph Neural Networks

UvA-Bosch Delta Lab(阿姆斯特丹大学-博世德尔塔实验室);University of Amsterdam(阿姆斯特丹大学)

Victor Garcia Satorras, Emiel Hoogeboom, Max Welling

摘要:

本文提出了一种新的学习与旋转、平移、反射和置换等变的图神经网络的模型,称为E(n)-等变图神经网络(EGNNs)。与现有的方法相比,我们的工作不需要在中间层计算昂贵的高阶表示,同时它仍然实现了竞争力或更好的性能。此外,尽管现有的方法仅限于三维空间上的等方差,但我们的模型很容易扩展到高维空间。我们证明了我们的方法对动力学系统建模,图自动编码器中的表示学习和预测分子性质的有效性。

英文摘要:

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.

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。

↑