A new perspective on building efficient and expressive 3D equivariant graph neural networks
Jul 28, 2023
Speakers
About
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these networks through a local-to-global analysis lacks today. In this paper, we propose a local hierarchy of 3D isomorphism to evaluate the expressive power of equivariant GNNs and investigate the process of representing global geometric information from local patches. Our work leads to two crucial modules for designing expressive and efficient geometric GNNs; namely local substructure encoding (\textbf{LSE}) and frame transition encoding (\textbf{FTE}). To demonstrate the applicability of our theory, we propose LEFTNet which effectively implements these modules and achieves state-of-the-art performance on both scalar-valued and vector-valued molecular property prediction tasks. We further point out the design space for future developments of equivariant graph neural networks.Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these networks through a local-to-global analysis lacks today. In this paper, we propose a local hierarchy of 3D isomorphism to evaluate the expressive power of equivariant GNNs and investigate the process of representing global geometric information from local patches. O…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Best of Both Worlds Policy Optimization
Watch later
MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action
Watch later
Geonho Hwang, …
Symmetry-Aware Robot Design
Watch later
Heng Dong, …
Training Large Language Models at Scale
Watch later
GNN and GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming
Watch later
Huigen Ye, …
