A Controlled Evaluation of Transfer Learning and Federated Meta-Learning for Privacy-Preserving Photonic Inverse Design

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Author: Ray, Rahul D
Format: Recurso digital
Published: Zenodo 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901158530908160
author Ray, Rahul D
author_facet Ray, Rahul D
contents <p>This paper presents a controlled empirical evaluation of three widely used learning paradigms—transfer learning, centralized model-agnostic meta-learning (MAML), and federated meta-learning—for few-shot photonic inverse design under structured physical domain shifts and privacy constraints.</p> <p>Using a large-scale synthetic dataset of 500,000 physics-consistent grating coupler simulations, the study constructs a non-IID learning scenario by partitioning data across federated clients based exclusively on a physically meaningful parameter (grating period). All methods are evaluated within a unified experimental framework that enforces identical neural architectures, optimization settings, data splits, and statistically stabilized evaluation protocols, enabling a fair and reproducible comparison.</p> <p>Results show that conventional transfer learning achieves the lowest absolute prediction error and strong zero-shot generalization across period-shifted regimes. In contrast, both centralized and federated MAML exhibit limited few-shot adaptation, with modest improvements as the number of support samples increases, but consistently underperforming the transfer baseline in absolute terms. Importantly, federated meta-learning achieves performance parity with centralized meta-learning across all evaluated settings, with no statistically significant degradation despite operating without access to raw client data.</p> <p>Rather than proposing new algorithms, this work focuses on clarifying the practical behavior and limitations of established few-shot and privacy-preserving learning paradigms in a physics-driven inverse regression setting. By explicitly reporting both positive and negative results under tightly controlled conditions, the study provides a reproducible benchmark for future research in photonic inverse design, scientific machine learning, and federated learning under physically structured data heterogeneity.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18147809
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle A Controlled Evaluation of Transfer Learning and Federated Meta-Learning for Privacy-Preserving Photonic Inverse Design
Ray, Rahul D
photonic inverse design
few-shot learning
transfer learning
federated learning
meta-learning
privacy-preserving machine learning
scientific machine learning
<p>This paper presents a controlled empirical evaluation of three widely used learning paradigms—transfer learning, centralized model-agnostic meta-learning (MAML), and federated meta-learning—for few-shot photonic inverse design under structured physical domain shifts and privacy constraints.</p> <p>Using a large-scale synthetic dataset of 500,000 physics-consistent grating coupler simulations, the study constructs a non-IID learning scenario by partitioning data across federated clients based exclusively on a physically meaningful parameter (grating period). All methods are evaluated within a unified experimental framework that enforces identical neural architectures, optimization settings, data splits, and statistically stabilized evaluation protocols, enabling a fair and reproducible comparison.</p> <p>Results show that conventional transfer learning achieves the lowest absolute prediction error and strong zero-shot generalization across period-shifted regimes. In contrast, both centralized and federated MAML exhibit limited few-shot adaptation, with modest improvements as the number of support samples increases, but consistently underperforming the transfer baseline in absolute terms. Importantly, federated meta-learning achieves performance parity with centralized meta-learning across all evaluated settings, with no statistically significant degradation despite operating without access to raw client data.</p> <p>Rather than proposing new algorithms, this work focuses on clarifying the practical behavior and limitations of established few-shot and privacy-preserving learning paradigms in a physics-driven inverse regression setting. By explicitly reporting both positive and negative results under tightly controlled conditions, the study provides a reproducible benchmark for future research in photonic inverse design, scientific machine learning, and federated learning under physically structured data heterogeneity.</p>
title A Controlled Evaluation of Transfer Learning and Federated Meta-Learning for Privacy-Preserving Photonic Inverse Design
topic photonic inverse design
few-shot learning
transfer learning
federated learning
meta-learning
privacy-preserving machine learning
scientific machine learning
url https://doi.org/10.5281/zenodo.18147809