Benchmarking Active Learning Strategies for Materials Optimization and Discovery

• URL: http://arxiv.org/abs/2204.05838v1
• Date: Tue, 12 Apr 2022 14:27:33 GMT
• Title: Benchmarking Active Learning Strategies for Materials Optimization and Discovery
• Authors: Alex Wang, Haotong Liang, Austin McDannald, Ichiro Takeuchi, A. Gilad Kusne
• Abstract summary: We present a reference dataset to benchmark active learning strategies in the form of various acquisition functions. We discuss the relationship between algorithm performance, materials search space, complexity, and the incorporation of prior knowledge.
• Score: 17.8738267360992
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous physical science is revolutionizing materials science. In these systems, machine learning controls experiment design, execution, and analysis in a closed loop. Active learning, the machine learning field of optimal experiment design, selects each subsequent experiment to maximize knowledge toward the user goal. Autonomous system performance can be further improved with implementation of scientific machine learning, also known as inductive bias-engineered artificial intelligence, which folds prior knowledge of physical laws (e.g., Gibbs phase rule) into the algorithm. As the number, diversity, and uses for active learning strategies grow, there is an associated growing necessity for real-world reference datasets to benchmark strategies. We present a reference dataset and demonstrate its use to benchmark active learning strategies in the form of various acquisition functions. Active learning strategies are used to rapidly identify materials with optimal physical properties within a ternary materials system. The data is from an actual Fe-Co-Ni thin-film library and includes previously acquired experimental data for materials compositions, X-ray diffraction patterns, and two functional properties of magnetic coercivity and the Kerr rotation. Popular active learning methods along with a recent scientific active learning method are benchmarked for their materials optimization performance. We discuss the relationship between algorithm performance, materials search space complexity, and the incorporation of prior knowledge.

Related papers

• Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes [70.66864668709677]
  We consider the problem of active learning for global sensitivity analysis of expensive black-box functions. Since function evaluations are expensive, we use active learning to prioritize experimental resources where they yield the most value. We propose novel active learning acquisition functions that directly target key quantities of derivative-based global sensitivity measures.
  arXiv  Detail & Related papers  (2024-07-13T01:41:12Z)
• Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions [3.0539022029583953]
  This thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. We investigate data subset selection techniques, specifically active learning and active sampling, grounded in information-theoretic principles.
  arXiv  Detail & Related papers  (2024-01-09T01:41:36Z)
• Symbolic Learning for Material Discovery [0.0]
  SyMDis is a sample efficient optimisation method based on symbolic learning. SyMDis performs comparably to a state-of-the-art optimiser, whilst learning interpretable rules to aid physical and chemical verification.
  arXiv  Detail & Related papers  (2023-11-30T15:56:00Z)
• Multimodal machine learning for materials science: composition-structure bimodal learning for experimentally measured properties [4.495968252019426]
  This paper introduces a novel approach to multimodal machine learning in materials science via composition-structure bimodal learning. The proposed COmposition-Structure Bimodal Network (COSNet) is designed to enhance learning and predictions of experimentally measured materials properties that have incomplete structure information.
  arXiv  Detail & Related papers  (2023-08-04T02:04:52Z)
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [64.55001982176226]
  LIBERO is a novel benchmark of lifelong learning for robot manipulation. We focus on how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:32:26Z)
• Advancing Reacting Flow Simulations with Data-Driven Models [50.9598607067535]
  Key to effective use of machine learning tools in multi-physics problems is to couple them to physical and computer models. The present chapter reviews some of the open opportunities for the application of data-driven reduced-order modeling of combustion systems.
  arXiv  Detail & Related papers  (2022-09-05T16:48:34Z)
• Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping [10.629434761354938]
  Science-informed AI or scientific AI has grown from a focus on data analysis to now controlling experiment design, simulation, execution and analysis in closed-loop autonomous systems. The CAMEO algorithm employs scientific AI to address two tasks: learning a material system's composition-structure relationship and identifying materials compositions with optimal functional properties.
  arXiv  Detail & Related papers  (2021-11-15T00:48:34Z)
• Rebuilding Trust in Active Learning with Actionable Metrics [77.99796068970569]
  Active Learning (AL) is an active domain of research, but is seldom used in the industry despite the pressing needs. This is in part due to a misalignment of objectives, while research strives at getting the best results on selected datasets. We present various actionable metrics to help rebuild trust of industrial practitioners in Active Learning.
  arXiv  Detail & Related papers  (2020-12-18T09:34:59Z)
• A User's Guide to Calibrating Robotics Simulators [54.85241102329546]
  This paper proposes a set of benchmarks and a framework for the study of various algorithms aimed to transfer models and policies learnt in simulation to the real world. We conduct experiments on a wide range of well known simulated environments to characterize and offer insights into the performance of different algorithms. Our analysis can be useful for practitioners working in this area and can help make informed choices about the behavior and main properties of sim-to-real algorithms.
  arXiv  Detail & Related papers  (2020-11-17T22:24:26Z)
• Probabilistic Active Meta-Learning [15.432006404678981]
  We introduce task selection based on prior experience into a meta-learning algorithm. We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.
  arXiv  Detail & Related papers  (2020-07-17T12:51:42Z)
• Bayesian active learning for production, a systematic study and a reusable library [85.32971950095742]
  In this paper, we analyse the main drawbacks of current active learning techniques. We do a systematic study on the effects of the most common issues of real-world datasets on the deep active learning process. We derive two techniques that can speed up the active learning loop such as partial uncertainty sampling and larger query size.
  arXiv  Detail & Related papers  (2020-06-17T14:51:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.