Federated Learning Approach for Lifetime Prediction of Semiconductor Lasers
Abstract
A new privacy-preserving federated learning framework allowing laser manufacturers to collaboratively build a robust ML-based laser lifetime prediction model, is proposed. It achieves a mean absolute error of 0.1 years and a significant performance improvement
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2022
- DOI:
- 10.48550/arXiv.2203.12414
- arXiv:
- arXiv:2203.12414
- Bibcode:
- 2022arXiv220312414A
- Keywords:
-
- Electrical Engineering and Systems Science - Signal Processing;
- Computer Science - Machine Learning
- E-Print:
- Optical Fiber Communication Conference (OFC 2022)