Deep Electromagnetic Structure Design Under Limited Evaluation Budgets

2025-06-24

AI Summary

To address the challenges of high-dimensional search spaces and expensive electromagnetic (EM) evaluations in EM structure design, this paper proposes a progressive quadtree search method. The method hierarchically partitions the design space via quadtree modeling—progressing adaptively from global coarse-grained to local fine-grained regions—and integrates a consistency-driven sample selection strategy to reduce reliance on high-fidelity surrogate models under limited evaluation budgets, thereby balancing exploration and exploitation. The framework unifies quadtree decomposition, progressive optimization, and consistency-based assessment to ensure both prediction reliability and efficient candidate generation. Evaluated on dual-band frequency-selective surface and high-gain antenna design tasks, the method reduces evaluation cost by 75%–85% and shortens design cycles by 20.27–38.80 days compared to state-of-the-art generative approaches, establishing an efficient and robust paradigm for high-performance EM structure design under data-scarce conditions.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Structured Learning
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

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 75-85%, effectively saving 20.27-38.80 days of product designing cycle.

Problem

• High-dimensional EMS design with expensive evaluations
• Data-intensive methods struggle with budget constraints
• Need efficient search under limited evaluation budgets

Innovation

• Progressive Quadtree-based Search (PQS) method
• Quad-tree hierarchical representation conversion
• Consistency-driven sample selection mechanism