Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization

2025-09-29

AI Summary

Generative AI for inverse design of novel materials often stagnates in low-quality regions, wasting computational resources. To address this, we propose a queue-priority-controlled active learning workflow. Our method embeds an active learning model directly into the generative pipeline to dynamically evaluate and rank candidate molecules, enabling online guidance and degradation suppression during generation. It integrates generative modeling, uncertainty-driven active learning, and a distributed queue scheduling mechanism to significantly enhance both search efficiency and candidate quality. In carbon-capture molecule discovery, the number of high-performing candidates validated by high-accuracy quantum chemical calculations increased from an average of 281 to 604—a 115% improvement—demonstrating the method’s effectiveness and practicality for efficient exploration of complex materials spaces.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Generative AI poses both opportunities and risks for solving inverse design problems in the sciences. Generative tools provide the ability to expand and refine a search space autonomously, but do so at the cost of exploring low-quality regions until sufficiently fine tuned. Here, we propose a queue prioritization algorithm that combines generative modeling and active learning in the context of a distributed workflow for exploring complex design spaces. We find that incorporating an active learning model to prioritize top design candidates can prevent a generative AI workflow from expending resources on nonsensical candidates and halt potential generative model decay. For an existing generative AI workflow for discovering novel molecular structure candidates for carbon capture, our active learning approach significantly increases the number of high-quality candidates identified by the generative model. We find that, out of 1000 novel candidates, our workflow without active learning can generate an average of 281 high-performing candidates, while our proposed prioritization with active learning can generate an average 604 high-performing candidates.

Problem

• Prioritizing generative AI candidates via active learning
• Preventing resource waste on low-quality material designs
• Enhancing novel molecular discovery for carbon capture

Innovation

• Queue prioritization algorithm combines generative modeling and active learning
• Active learning model prioritizes top design candidates to prevent resource waste
• Prioritization approach significantly increases high-quality candidate identification