E (n) equivariant graph neural networks
VG Satorras, E Hoogeboom… - … conference on machine …, 2021 - proceedings.mlr.press
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 …
translations, reflections and permutations called E (n)-Equivariant Graph Neural Networks …
E (n) equivariant normalizing flows
V Garcia Satorras, E Hoogeboom… - Advances in …, 2021 - proceedings.neurips.cc
This paper introduces a generative model equivariant to Euclidean symmetries: E (n)
Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E (n) …
Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E (n) …
Machine learning and physics: A survey of integrated models
A Seyyedi, M Bohlouli, SN Oskoee - ACM Computing Surveys, 2023 - dl.acm.org
Predictive modeling of various systems around the world is extremely essential from the
physics and engineering perspectives. The recognition of different systems and the capacity …
physics and engineering perspectives. The recognition of different systems and the capacity …
Artificial intelligence for science in quantum, atomistic, and continuum systems
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 …
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …
When physics meets machine learning: A survey of physics-informed machine learning
Physics-informed machine learning (PIML), referring to the combination of prior knowledge
of physics, which is the high level abstraction of natural phenomenons and human …
of physics, which is the high level abstraction of natural phenomenons and human …
Coordinate Independent Convolutional Networks--Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
Motivated by the vast success of deep convolutional networks, there is a great interest in
generalizing convolutions to non-Euclidean manifolds. A major complication in comparison …
generalizing convolutions to non-Euclidean manifolds. A major complication in comparison …
Physics-embedded neural networks: Graph neural pde solvers with mixed boundary conditions
Graph neural network (GNN) is a promising approach to learning and predicting physical
phenomena described in boundary value problems, such as partial differential equations …
phenomena described in boundary value problems, such as partial differential equations …
The symplectic adjoint method: Memory-efficient backpropagation of neural-network-based differential equations
T Matsubara, Y Miyatake… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The combination of neural networks and numerical integration can provide highly accurate
models of continuous-time dynamical systems and probabilistic distributions. However, if a …
models of continuous-time dynamical systems and probabilistic distributions. However, if a …
[PDF][PDF] Physics-embedded neural networks: E (n)-equivariant graph neural pde solvers
Graph neural network (GNN) is a promising approach to learning and predicting physical
phenomena described in boundary value problems, such as partial differential equations …
phenomena described in boundary value problems, such as partial differential equations …
Revisiting transformation invariant geometric deep learning: Are initial representations all you need?
Geometric deep learning, ie, designing neural networks to handle the ubiquitous geometric
data such as point clouds and graphs, have achieved great successes in the last decade …
data such as point clouds and graphs, have achieved great successes in the last decade …