Search Results for author:
Found 6 papers, 1 papers with code
Symmetry Breaking and Equivariant Neural Networks
Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design.
Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node.
Equivariant Networks for Crystal Structures
Supervised learning with deep models has tremendous potential for applications in materials science.
Equivariance with Learned Canonicalization Functions
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations.
Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests
Crystal graph convolutional neural networks (CGCNN), materials graph network (MEGNet) and random forests are trained on the Materials Project database that contains the results of high-throughput DFT predictions.
Gradient Starvation: A Learning Proclivity in Neural Networks
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
