Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Conferences > OFC > 2024 > M1H > M1H.3

Analysis and Mitigation of Unwanted Biases in ML-based QoT Classification Tasks

Carlos Natalino, Behnam Shariati, Pooyan Safari, Johannes Karl Fischer, and Paolo Monti

Not Accessible

Your library or personal account may give you access

Abstract

We address the problem of mitigating biases in models used for the quality of transmission prediction. The proposed method reduces the relative accuracy difference between samples with different feature values by up to 45%.

© 2024 The Author(s)

PDF Article
More Like This
QoT Estimation for Large-scale Mixed-rate Disaggregated Metro DCI Networks by Artificial Neural Networks

Yan He, Kausthubh Chandramouli, Zhiqun Zhai, Sai Chen, Liang Dou, Chongjin Xie, Chao Lu, and Alan Pak Tao Lau
W3G.2 Optical Fiber Communication Conference (OFC) 2024

Quantifying Features’ Contribution for ML-based Quality-of-Transmission Estimation using Explainable AI

Omran Ayoub, Davide Andreoletti, Sebastian Troia, Silvia Giordano, Andrea Bianco, and Cristina Rottondi
We3B.4 European Conference and Exhibition on Optical Communication (ECOC) 2022

CompQoTE: Generalizing QoT Estimation with Composable ML and End-to-End Learning

Hanyu Gao, Xiaoliang Chen, Lu Sun, and Zhaohui Li
W4G.1 Optical Fiber Communication Conference (OFC) 2023

View More...
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use