Picture for Massimiliano Lupo Pasini

Massimiliano Lupo Pasini

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Add code
Apr 10, 2025
Viaarxiv icon

Scalable Training of Graph Foundation Models for Atomistic Materials Modeling: A Case Study with HydraGNN

Add code
Jun 12, 2024
Viaarxiv icon

DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies

Add code
Oct 11, 2023
Figure 1 for DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Figure 2 for DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Figure 3 for DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Figure 4 for DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Viaarxiv icon

A deep learning approach to solve forward differential problems on graphs

Add code
Oct 07, 2022
Figure 1 for A deep learning approach to solve forward differential problems on graphs
Figure 2 for A deep learning approach to solve forward differential problems on graphs
Figure 3 for A deep learning approach to solve forward differential problems on graphs
Figure 4 for A deep learning approach to solve forward differential problems on graphs
Viaarxiv icon

A deep learning approach for detection and localization of leaf anomalies

Add code
Oct 07, 2022
Figure 1 for A deep learning approach for detection and localization of leaf anomalies
Figure 2 for A deep learning approach for detection and localization of leaf anomalies
Figure 3 for A deep learning approach for detection and localization of leaf anomalies
Figure 4 for A deep learning approach for detection and localization of leaf anomalies
Viaarxiv icon

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks

Add code
Jul 25, 2022
Figure 1 for Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Figure 2 for Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Figure 3 for Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Figure 4 for Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Viaarxiv icon

Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules

Add code
Jul 22, 2022
Figure 1 for Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
Figure 2 for Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
Figure 3 for Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
Figure 4 for Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
Viaarxiv icon

Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data

Add code
Apr 01, 2022
Figure 1 for Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data
Figure 2 for Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data
Figure 3 for Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data
Figure 4 for Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data
Viaarxiv icon

Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems

Add code
Feb 04, 2022
Figure 1 for Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
Figure 2 for Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
Figure 3 for Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
Figure 4 for Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
Viaarxiv icon

Stable Anderson Acceleration for Deep Learning

Add code
Oct 26, 2021
Figure 1 for Stable Anderson Acceleration for Deep Learning
Figure 2 for Stable Anderson Acceleration for Deep Learning
Figure 3 for Stable Anderson Acceleration for Deep Learning
Figure 4 for Stable Anderson Acceleration for Deep Learning
Viaarxiv icon