PAL -- Parallel active learning for machine-learned potentials

TL;DR

PAL is an automated, parallel active learning library that enhances the efficiency and scalability of machine learning model training by leveraging MPI-based parallelism on CPU and GPU systems.

Contribution

This work introduces PAL, a modular library that automates and parallelizes active learning workflows, significantly reducing computational overhead and improving scalability for scientific applications.

Findings

PAL achieves substantial speed-ups through asynchronous parallelization.

PAL effectively reduces computational overhead in active learning workflows.

Applications demonstrate PAL's ability to accelerate model development in various scientific domains.

Abstract

Constructing datasets representative of the target domain is essential for training effective machine learning models. Active learning (AL) is a promising method that iteratively extends training data to enhance model performance while minimizing data acquisition costs. However, current AL workflows often require human intervention and lack parallelism, leading to inefficiencies and underutilization of modern computational resources. In this work, we introduce PAL, an automated, modular, and parallel active learning library that integrates AL tasks and manages their execution and communication on shared- and distributed-memory systems using the Message Passing Interface (MPI). PAL provides users with the flexibility to design and customize all components of their active learning scenarios, including machine learning models with uncertainty estimation, oracles for ground truth labeling, and strategies for exploring the target space. We demonstrate that PAL significantly reduces computational overhead and improves scalability, achieving substantial speed-ups through asynchronous parallelization on CPU and GPU hardware. Applications of PAL to several real-world scenarios - including ground-state reactions in biomolecular systems, excited-state dynamics of molecules, simulations of inorganic clusters, and thermo-fluid dynamics - illustrate its effectiveness in accelerating the development of machine learning models. Our results show that PAL enables efficient utilization of high-performance computing resources in active learning workflows, fostering advancements in scientific research and engineering applications.