Saved in:
Bibliographic Details
Main Authors: Tziouvaras, Athanasios, Bertalanic, Blaz, Floros, George, Kolomvatsos, Kostas, Sarigiannidis, Panagiotis, Fortuna, Carolina
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.10325
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911334109544448
author Tziouvaras, Athanasios
Bertalanic, Blaz
Floros, George
Kolomvatsos, Kostas
Sarigiannidis, Panagiotis
Fortuna, Carolina
author_facet Tziouvaras, Athanasios
Bertalanic, Blaz
Floros, George
Kolomvatsos, Kostas
Sarigiannidis, Panagiotis
Fortuna, Carolina
contents AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models and lead to undesired behaviors. To counter for undetected model degradation, we propose ALERT; a method that can detect feature distribution changes and trigger model re-training that works well on two wireless network use cases: wireless fingerprinting and link anomaly detection. ALERT includes three components: representation learning, statistical testing and utility assessment. We rely on MLP for designing the representation learning component, on Kolmogorov-Smirnov and Population Stability Index tests for designing the statistical testing and a new function for utility assessment. We show the superiority of the proposed method against ten standard drift detection methods available in the literature on two wireless network use cases.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10325
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Representation Learning Approach to Feature Drift Detection in Wireless Networks
Tziouvaras, Athanasios
Bertalanic, Blaz
Floros, George
Kolomvatsos, Kostas
Sarigiannidis, Panagiotis
Fortuna, Carolina
Machine Learning
AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models and lead to undesired behaviors. To counter for undetected model degradation, we propose ALERT; a method that can detect feature distribution changes and trigger model re-training that works well on two wireless network use cases: wireless fingerprinting and link anomaly detection. ALERT includes three components: representation learning, statistical testing and utility assessment. We rely on MLP for designing the representation learning component, on Kolmogorov-Smirnov and Population Stability Index tests for designing the statistical testing and a new function for utility assessment. We show the superiority of the proposed method against ten standard drift detection methods available in the literature on two wireless network use cases.
title A Representation Learning Approach to Feature Drift Detection in Wireless Networks
topic Machine Learning
url https://arxiv.org/abs/2505.10325