Graph Neural Networks (GNNs) are a powerful tool for handling structured...
As deep learning models grow, sparsity is becoming an increasingly criti...
Many data have an underlying dependence on spatial location; it may be
w...
Graph databases (GDBs) enable processing and analysis of unstructured,
c...
Post-processing ensemble prediction systems can improve weather forecast...
Rapid progress in deep learning is leading to a diverse set of quickly
c...
We present a graph neural network to learn graph coloring heuristics usi...
The growing energy and performance costs of deep learning have driven th...
I/O is emerging as a major bottleneck for machine learning training,
esp...
We present scalable hybrid-parallel algorithms for training large-scale ...
Transformers have become widely used for language modeling and sequence
...
We present Shapeshifter Networks (SSNs), a flexible neural network frame...
Quantifying uncertainty in weather forecasts typically employs ensemble
...
Deep learning at scale is dominated by communication time. Distributing
...
Modern weather forecast models perform uncertainty quantification using
...
Scaling CNN training is necessary to keep up with growing datasets and r...