Following a fast initial breakthrough in graph-based learning, Graph Neural Networks
(GNNs) have reached a widespread application in many science and engineering fields …

We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint
generation of antibody 3D structures and sequences. AbDiffuser is built on top of a new …

Graph neural networks that model 3D data, such as point clouds or atoms, are typically
desired to be $ SO (3) $ equivariant, ie, equivariant to 3D rotations. Unfortunately …

Applications of machine learning techniques for materials modeling typically involve
functions that are known to be equivariant or invariant to specific symmetries. While graph …

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …

Symmetry-based neural networks often constrain the architecture in order to achieve
invariance or equivariance to a group of transformations. In this paper, we propose an …

We introduce SignNet and BasisNet--new neural architectures that are invariant to two key
symmetries displayed by eigenvectors:(i) sign flips, since if $ v $ is an eigenvector then so is …

Abstract Graph Neural Networks (GNN) are inherently limited in their expressive power.
Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler …

Point clouds are versatile representations of 3D objects and have found widespread
application in science and engineering. Many successful deep-learning models have been …

Equivariant networks are specifically designed to ensure consistent behavior with respect to
a set of input transformations, leading to higher sample efficiency and more accurate and …