Smooth, exact rotational symmetrization for deep learning on point clouds | Sergey Pozdnyakov

Portal is the home of the AI for drug discovery community. Join for more details on this talk and to connect with the speakers: portal.valencelabs.com/logg
Abstract: Point clouds are versatile representations of 3D objects and have found widespread application in science and engineering. Many successful deep-learning models have been proposed that use them as input. The domain of chemical and materials modeling is especially challenging because exact compliance with physical constraints is highly desirable for a model to be usable in practice. These constraints include smoothness and invariance with respect to translations, rotations, and permutations of identical atoms. If these requirements are not rigorously fulfilled, atomistic simulations might lead to absurd outcomes even if the model has excellent accuracy. Consequently, dedicated architectures, which achieve invariance by restricting their design space, have been developed. General-purpose point-cloud models are more varied but often disregard rotational symmetry. We propose a general symmetrization method that adds rotational equivariance to any given model while preserving all the other requirements. Our approach simplifies the development of better atomic-scale machine-learning schemes by relaxing the constraints on the design space and making it possible to incorporate ideas that proved effective in other domains. We demonstrate this idea by introducing the Point Edge Transformer (PET) architecture, which is not intrinsically equivariant but achieves state-of-the-art performance on several benchmark datasets of molecules and solids. A-posteriori application of our general protocol makes PET exactly equivariant, with minimal changes to its accuracy.
Speakers: Sergey Pozdnyakov
Twitter Hannes: / hannesstaerk
Twitter Dominique: / dom_beaini
~
Chapters
00:00 - Intro + Background
11:15 - Equivariant Coordinate System Ensemble
27:50 - Computational Cost
31:45 - Adaptive Cutoff
38:05 - Impact of beta
45:25 - Smoothness
48:31 - Related Work
54:07 - Point Edge Transformer
1:09:07 - Q+A