TY - GEN
T1 - Clustering Mobile Network Data with Decorrelating Adversarial Nets
AU - Kajo, Marton
AU - Schnellbach, Janik
AU - Mwanje, Stephen S.
AU - Carle, Georg
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Deep learning plays a crucial role in enabling cognitive automation for the mobile networks of the future. Deep clustering - a subset of deep learning - is a valuable tool for many network automation use cases. Unfortunately, most state-of-the-art clustering algorithms target image datasets, which makes them hard to apply to mobile network automation due to their highly tuned nature and assumptions about the data. In this paper, we propose a new algorithm, Decorrelating Adversarial Nets for Clustering-friendly Encoding (DANCE), intended to be a reliable deep clustering method for mobile network automation use cases. DANCE uses a reconstructive clustering approach, separating clustering-relevant from clustering-irrelevant features in a latent representation. This separation removes unnecessary information from the clustering, increasing consistency and peak performance. We comprehensively evaluate DANCE and other select state-of-the-art deep clustering algorithms, and show that DANCE outperforms these algorithms by a significant margin in a mobile user behavior clustering task based on data gained from a simulated scenario.
AB - Deep learning plays a crucial role in enabling cognitive automation for the mobile networks of the future. Deep clustering - a subset of deep learning - is a valuable tool for many network automation use cases. Unfortunately, most state-of-the-art clustering algorithms target image datasets, which makes them hard to apply to mobile network automation due to their highly tuned nature and assumptions about the data. In this paper, we propose a new algorithm, Decorrelating Adversarial Nets for Clustering-friendly Encoding (DANCE), intended to be a reliable deep clustering method for mobile network automation use cases. DANCE uses a reconstructive clustering approach, separating clustering-relevant from clustering-irrelevant features in a latent representation. This separation removes unnecessary information from the clustering, increasing consistency and peak performance. We comprehensively evaluate DANCE and other select state-of-the-art deep clustering algorithms, and show that DANCE outperforms these algorithms by a significant margin in a mobile user behavior clustering task based on data gained from a simulated scenario.
KW - clustering
KW - cognitive network automation
KW - deep learning
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85133171453&partnerID=8YFLogxK
U2 - 10.1109/NOMS54207.2022.9789825
DO - 10.1109/NOMS54207.2022.9789825
M3 - Conference contribution
AN - SCOPUS:85133171453
T3 - Proceedings of the IEEE/IFIP Network Operations and Management Symposium 2022: Network and Service Management in the Era of Cloudification, Softwarization and Artificial Intelligence, NOMS 2022
BT - Proceedings of the IEEE/IFIP Network Operations and Management Symposium 2022
A2 - Varga, Pal
A2 - Granville, Lisandro Zambenedetti
A2 - Galis, Alex
A2 - Godor, Istvan
A2 - Limam, Noura
A2 - Chemouil, Prosper
A2 - Francois, Jerome
A2 - Pahl, Marc-Oliver
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/IFIP Network Operations and Management Symposium, NOMS 2022
Y2 - 25 April 2022 through 29 April 2022
ER -