Deep Electromagnetic Structure Design Under Limited Evaluation Budgets

Shijian Zheng, Fangxiao Jin, Shuhai Zhang, Quan Xue, Mingkui Tan
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78170-78189, 2025.

Abstract

Electromagnetic structure (EMS) design plays a critical role in developing advanced antennas and materials, but remains challenging due to high-dimensional design spaces and expensive evaluations. While existing methods commonly employ high-quality predictors or generators to alleviate evaluations, they are often data-intensive and struggle with real-world scale and budget constraints. To address this, we propose a novel method called Progressive Quadtree-based Search (PQS). Rather than exhaustively exploring the high-dimensional space, PQS converts the conventional image-like layout into a quadtree-based hierarchical representation, enabling a progressive search from global patterns to local details. Furthermore, to lessen reliance on highly accurate predictors, we introduce a consistency-driven sample selection mechanism. This mechanism quantifies the reliability of predictions, balancing exploitation and exploration when selecting candidate designs. We evaluate PQS on two real-world engineering tasks, i.e., Dual-layer Frequency Selective Surface and High-gain Antenna. Experimental results show that our method can achieve satisfactory designs under limited computational budgets, outperforming baseline methods. In particular, compared to generative approaches, it cuts evaluation costs by 75$\tilde$85%, effectively saving 20.27$\tilde$38.80 days of product designing cycle.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zheng25g, title = {Deep Electromagnetic Structure Design Under Limited Evaluation Budgets}, author = {Zheng, Shijian and Jin, Fangxiao and Zhang, Shuhai and Xue, Quan and Tan, Mingkui}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {78170--78189}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zheng25g/zheng25g.pdf}, url = {https://proceedings.mlr.press/v267/zheng25g.html}, abstract = {Electromagnetic structure (EMS) design plays a critical role in developing advanced antennas and materials, but remains challenging due to high-dimensional design spaces and expensive evaluations. While existing methods commonly employ high-quality predictors or generators to alleviate evaluations, they are often data-intensive and struggle with real-world scale and budget constraints. To address this, we propose a novel method called Progressive Quadtree-based Search (PQS). Rather than exhaustively exploring the high-dimensional space, PQS converts the conventional image-like layout into a quadtree-based hierarchical representation, enabling a progressive search from global patterns to local details. Furthermore, to lessen reliance on highly accurate predictors, we introduce a consistency-driven sample selection mechanism. This mechanism quantifies the reliability of predictions, balancing exploitation and exploration when selecting candidate designs. We evaluate PQS on two real-world engineering tasks, i.e., Dual-layer Frequency Selective Surface and High-gain Antenna. Experimental results show that our method can achieve satisfactory designs under limited computational budgets, outperforming baseline methods. In particular, compared to generative approaches, it cuts evaluation costs by 75$\tilde$85%, effectively saving 20.27$\tilde$38.80 days of product designing cycle.} }
Endnote
%0 Conference Paper %T Deep Electromagnetic Structure Design Under Limited Evaluation Budgets %A Shijian Zheng %A Fangxiao Jin %A Shuhai Zhang %A Quan Xue %A Mingkui Tan %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zheng25g %I PMLR %P 78170--78189 %U https://proceedings.mlr.press/v267/zheng25g.html %V 267 %X Electromagnetic structure (EMS) design plays a critical role in developing advanced antennas and materials, but remains challenging due to high-dimensional design spaces and expensive evaluations. While existing methods commonly employ high-quality predictors or generators to alleviate evaluations, they are often data-intensive and struggle with real-world scale and budget constraints. To address this, we propose a novel method called Progressive Quadtree-based Search (PQS). Rather than exhaustively exploring the high-dimensional space, PQS converts the conventional image-like layout into a quadtree-based hierarchical representation, enabling a progressive search from global patterns to local details. Furthermore, to lessen reliance on highly accurate predictors, we introduce a consistency-driven sample selection mechanism. This mechanism quantifies the reliability of predictions, balancing exploitation and exploration when selecting candidate designs. We evaluate PQS on two real-world engineering tasks, i.e., Dual-layer Frequency Selective Surface and High-gain Antenna. Experimental results show that our method can achieve satisfactory designs under limited computational budgets, outperforming baseline methods. In particular, compared to generative approaches, it cuts evaluation costs by 75$\tilde$85%, effectively saving 20.27$\tilde$38.80 days of product designing cycle.
APA
Zheng, S., Jin, F., Zhang, S., Xue, Q. & Tan, M.. (2025). Deep Electromagnetic Structure Design Under Limited Evaluation Budgets. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:78170-78189 Available from https://proceedings.mlr.press/v267/zheng25g.html.

Related Material