Federated Representation Learning for Encrypted Application Type Classification in beyond 5G RAN

Sid Ali Hamideche (1, 2) , Marie Line Alberi Morel (3) , Kamal Singh (4, 5) , César Viho (2, 1)

1 ERMINE - mEasuRing and ManagIng Network operation and Economic
2 IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires
3 Nokia Bell Labs [Nozay]
4 UJM - Université Jean Monnet - Saint-Étienne
5 LabHC - Laboratoire Hubert Curien

Mobile application classification is essential for advanced network management and application-based QoS policy enforcement in future, AI-enhanced, beyond 5G and 6G mobile networks. This article proposes to use AI methods to categorize applications as functional types (e.g., Video, Audio, Browsing) despite encryption and limited labeled data. We tackle these challenges through unsupervised representation learning, which maximizes the use of abundant unlabeled data in mobile networks. Due to the distributed nature of beyond 5G and 6G networks, we use this method in federated learning scenarios and compare it to the centralized ones. Our findings highlight that unsupervised learning improves model performance, especially with scarce labeled data. Additionally, federated learning provides effective results as compared to centralized methods.

Keywords: Application classification; Beyond 5G; 6G; Deep learning; Representation learning; Federated learning

Domains: Computer Science [cs]; Machine Learning [cs.LG]; Networking and Internet Architecture [cs.NI]

Sid Ali Hamideche, Marie Line Alberi Morel, Kamal Singh, César Viho. Federated Representation Learning for Encrypted Application Type Classification in beyond 5G RAN. IEEE Consumer Communications and Networking Conference, IEEE, Jan 2025, Las Vegas, United States. ⟨hal-04771982⟩