21 citations · 76 across the 23 of their papers we have counts for
26 papers
Scaling Laws for Physics-Aware ACOPF Surrogate Learning
Yijiang Li, Emon Dey, Stefano Fenu +3
Learning-based surrogates for AC optimal power flow (ACOPF) promise large speedups over classical solvers, but their operational value depends on physical feasibility as much as pr…
Automated Data Readiness for Scientific AI
Sean R. Wilkinson, Valentine G. Anantharaj, Jong Youl Choi +8
Leadership computing facilities steward large-scale scientific datasets that routinely require substantial transformation before serving as AI training data. However, no existing f…
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
Alessio Barboni, Massimiliano Lupo Pasini, Bishal Lakha +1
Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond. However, current…
Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
Massimiliano Lupo Pasini, Yijiang Li, Kibaek Kim +1
Fast and reliable optimal power flow (OPF) approximation is important for power system operation, yet heterogeneous OPF graph models are often evaluated either with architecture-sp…
Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data
Massimiliano Lupo Pasini, Jong Youl Choi, Kshitij Mehta +8
We present an exascale workflow for materials discovery using atomistic graph foundation models built on HydraGNN. We jointly train on 16 open first-principles datasets (544+ milli…
When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Arindam Chowdhury, Massimiliano Lupo Pasini
Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their…
Multi-task parallelism for robust pre-training of graph foundation models on multi-source, multi-fidelity atomistic modeling data
Massimiliano Lupo Pasini, Jong Youl Choi, Pei Zhang +6
Graph foundation models using graph neural networks promise sustainable, efficient atomistic modeling. To tackle challenges of processing multi-source, multi-fidelity data during p…
Two-Level Sketching Alternating Anderson acceleration for Complex Physics Applications
Nicolás A. Barnafi, Massimiliano Lupo Pasini
We present a novel two-level sketching extension of the Alternating Anderson-Picard (AAP) method for accelerating fixed-point iterations in challenging single- and multi-physics si…
Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling
Chaojian Li, Zhifan Ye, Massimiliano Lupo Pasini +4
Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science, where accurate predictions of the target material property…
Real-time interpretation of neutron vibrational spectra with symmetry-equivariant Hessian matrix prediction
Bowen Han, Pei Zhang, Kshitij Mehta +3
The vibrational behavior of molecules serves as a crucial fingerprint of their structure, chemical state, and surrounding environment. Neutron vibrational spectroscopy provides com…
Scalable Training of Trustworthy and Energy-Efficient Predictive Graph Foundation Models for Atomistic Materials Modeling: A Case Study with HydraGNN
Massimiliano Lupo Pasini, Jong Youl Choi, Kshitij Mehta +8
We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutio…
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang +89
In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences. This could herald a new era of scient…
A deep learning approach for adaptive zoning
Massimiliano Lupo Pasini, Luka Malenica, Kwitae Chong +1
We propose a supervised deep learning (DL) approach to perform adaptive zoning on time dependent partial differential equations that model the propagation of 1D shock waves in a co…
A deep learning approach to solve forward differential problems on graphs
Yuanyuan Zhao, Massimiliano Lupo Pasini
We propose a novel deep learning (DL) approach to solve one-dimensional non-linear elliptic, parabolic, and hyperbolic problems on graphs. A system of physics-informed neural netwo…
A deep learning approach for detection and localization of leaf anomalies
Davide Calabrò, Massimiliano Lupo Pasini, Nicola Ferro +1
The detection and localization of possible diseases in crops are usually automated by resorting to supervised deep learning approaches. In this work, we tackle these goals with uns…
A Neural Network Approach to Predict Gibbs Free Energy of Ternary Solid Solutions
Paul Laiu, Ying Yang, Massimiliano Lupo Pasini +2
We present a data-centric deep learning (DL) approach using neural networks (NNs) to predict the thermodynamics of ternary solid solutions. We explore how NNs can be trained with a…
Machine Learning for First Principles Calculations of Material Properties for Ferromagnetic Materials
Markus Eisenbach, Mariia Karabin, Massimiliano Lupo Pasini +1
The investigation of finite temperature properties using Monte-Carlo (MC) methods requires a large number of evaluations of the system's Hamiltonian to sample the phase space neede…
Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Massimiliano Lupo Pasini, Junqi Yin
We propose a stable, parallel approach to train Wasserstein Conditional Generative Adversarial Neural Networks (W-CGANs) under the constraint of a fixed computational budget. Diffe…
Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
Jong Youl Choi, Pei Zhang, Kshitij Mehta +2
Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecu…
Anderson acceleration with approximate calculations: applications to scientific computing
Massimiliano Lupo Pasini, M. Paul Laiu
We provide rigorous theoretical bounds for Anderson acceleration (AA) that allow for approximate calculations when applied to solve linear problems. We show that, when the approxim…
Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data
Massimiliano Lupo Pasini, Simona Perotto
We propose a new approach to generate a reliable reduced model for a parametric elliptic problem, in the presence of noisy data. The reference model reduction procedure is the dire…
Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
Massimiliano Lupo Pasini, Pei Zhang, Samuel Temple Reeve +1
We introduce a multi-tasking graph convolutional neural network, HydraGNN, to simultaneously predict both global and atomic physical properties and demonstrate with ferromagnetic m…
Stable Anderson Acceleration for Deep Learning
Massimiliano Lupo Pasini, Junqi Yin, Viktor Reshniak +1
Anderson acceleration (AA) is an extrapolation technique designed to speed-up fixed-point iterations like those arising from the iterative training of DL models. Training DL models…
Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
Massimiliano Lupo Pasini, Vittorio Gabbi, Junqi Yin +2
We propose a distributed approach to train deep convolutional generative adversarial neural network (DC-CGANs) models. Our method reduces the imbalance between generator and discri…