Scholarlink

<p>Efficient and robust optimization is important in material science for identifying optimal structural parameters and enhancing material performance. Surrogate-based active learning algorithms have recently gained great attention for their ability to efficiently navigate large, high-dimensional design spaces. Among surrogate models, 2<sup>nd</sup>-order factorization machine (FM) models are widely employed as the surrogate model in active learning algorithms due to their balance between simplicity and effectiveness. However, their quadratic nature limits their capacity to capture complex, higher-order interactions among variables, often leading to suboptimal solutions. To overcome this limitation, we propose an active learning scheme integrating a 3<sup>rd</sup>-order FM model, capable of modeling three-variable interactions and more intricate relationships in material systems. We comprehensively evaluate the surrogate modeling performance of the 3<sup>rd</sup>-order FM case using various objective functions. Furthermore, we examine the optimization reliability and efficiency of the 3<sup>rd</sup>-order FM-based active learning in a real-world material design task (e.g., nanophotonic structures for transparent radiative cooling). Our study shows that the 3<sup>rd</sup>-order FM outperforms the 2<sup>nd</sup>-order model in both surrogate accuracy and optimization performance, highlighting higher-order models’ promises for material design and optimization problems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Higher-order factorization machine for accurate surrogate modeling in material design

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月9日

查看全文
  • Sanghyo Hwang,
  • Seongmin Kim,
  • Zhihao Xu,
  • Tengfei Luo,
  • Eungkyu Lee

摘要

Efficient and robust optimization is important in material science for identifying optimal structural parameters and enhancing material performance. Surrogate-based active learning algorithms have recently gained great attention for their ability to efficiently navigate large, high-dimensional design spaces. Among surrogate models, 2nd-order factorization machine (FM) models are widely employed as the surrogate model in active learning algorithms due to their balance between simplicity and effectiveness. However, their quadratic nature limits their capacity to capture complex, higher-order interactions among variables, often leading to suboptimal solutions. To overcome this limitation, we propose an active learning scheme integrating a 3rd-order FM model, capable of modeling three-variable interactions and more intricate relationships in material systems. We comprehensively evaluate the surrogate modeling performance of the 3rd-order FM case using various objective functions. Furthermore, we examine the optimization reliability and efficiency of the 3rd-order FM-based active learning in a real-world material design task (e.g., nanophotonic structures for transparent radiative cooling). Our study shows that the 3rd-order FM outperforms the 2nd-order model in both surrogate accuracy and optimization performance, highlighting higher-order models’ promises for material design and optimization problems.