Generalized few-shot transfer learning architecture for modeling the EDFA gain spectrum

TL;DR

This paper introduces a semi-supervised, transfer learning neural network architecture for accurate EDFA gain spectrum modeling, reducing measurement needs and improving prediction accuracy across different EDFA types.

Contribution

It presents a novel SS-NN model with a two-phase training strategy and transfer learning techniques, including covariance matching, for both homogeneous and heterogeneous EDFA domain adaptation.

Findings

Significantly reduces measurement requirements.

Achieves lower mean absolute errors.

Improves error distribution over benchmarks.

Abstract

Accurate modeling of the gain spectrum in Erbium-Doped Fiber Amplifiers (EDFAs) is essential for optimizing optical network performance, particularly as networks evolve toward multi-vendor solutions. In this work, we propose a generalized few-shot transfer learning architecture based on a Semi-Supervised Self-Normalizing Neural Network (SS-NN) that leverages internal EDFA features - such as VOA input or output power and attenuation, to improve gain spectrum prediction. Our SS-NN model employs a two-phase training strategy comprising unsupervised pre-training with noise-augmented measurements and supervised fine-tuning with a custom weighted MSE loss. Furthermore, we extend the framework with transfer learning (TL) techniques that enable both homogeneous (same-feature space) and heterogeneous (different-feature sets) model adaptation across booster, preamplifier, and ILA EDFAs. To address feature mismatches in heterogeneous TL, we incorporate a covariance matching loss to align second-order feature statistics between source and target domains. Extensive experiments conducted across 26 EDFAs in the COSMOS and Open Ireland testbeds demonstrate that the proposed approach significantly reduces the number of measurements requirements on the system while achieving lower mean absolute errors and improved error distributions compared to benchmark methods.