Analysis and Mitigation of Unwanted Biases in ML-based QoT Classification Tasks
Paper i proceeding, 2024
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%.
Machine learning
Quality of transmission
Classification
Optical networks
Författare
Carlos Natalino Da Silva
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Behnam Shariati
Fraunhofer-Institut fur Nachrichtentechnik Heinrich-Hertz-Institut - HHI
Pooyan Safari
Fraunhofer-Institut fur Nachrichtentechnik Heinrich-Hertz-Institut - HHI
Johannes Fischer
Fraunhofer-Institut fur Nachrichtentechnik Heinrich-Hertz-Institut - HHI
Paolo Monti
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Conference on Optical Fiber Communication, Technical Digest Series
M1H.3
9781957171326 (ISBN)
Optical Fiber Communications Conference and Exhibition (OFC)
San Diego, CA, USA,
San Diego, CA, USA,
Providing Resilient & secure networks [Operating on Trusted Equipment] to CriTical infrastructures (PROTECT)
VINNOVA (2020-03506), 2021-02-01 -- 2024-01-31.
Styrkeområden
Informations- och kommunikationsteknik
Ämneskategorier
Telekommunikation
Kommunikationssystem
Signalbehandling
DOI
10.1364/OFC.2024.M1H.3
ISBN
9781957171326