4 papers · 1 filter
An Efficient Sparse Kernel Generator for O(3)-Equivariant Deep Networks
Vivek Bharadwaj, Austin Glover, Aydin Buluc +1
Rotation equivariant graph neural networks, i.e. networks designed to guarantee certain geometric relations between their inputs and outputs, yield state of the art performance on…
Sparsity-Aware Communication for Distributed Graph Neural Network Training
Ujjaini Mukhodopadhyay, Alok Tripathy, Oguz Selvitopi +2
Graph Neural Networks (GNNs) are a computationally efficient method to learn embeddings and classifications on graph data. However, GNN training has low computational intensity, ma…
Scaling Graph Neural Networks for Particle Track Reconstruction
Alok Tripathy, Alina Lazar, Xiangyang Ju +3
Particle track reconstruction is an important problem in high-energy physics (HEP), necessary to study properties of subatomic particles. Traditional track reconstruction algorithm…
Distributed Matrix-Based Sampling for Graph Neural Network Training
Alok Tripathy, Katherine Yelick, Aydin Buluc
Graph Neural Networks (GNNs) offer a compact and computationally efficient way to learn embeddings and classifications on graph data. GNN models are frequently large, making distri…