Leveraging triplet loss and nonlinear dimensionality reduction for on-the-fly channel charting

Taha Yassine (1, 2) , Luc Le Magoarou (1) , Stéphane Paquelet (1) , Matthieu Crussière (1, 3, 2)

1 IRT b-com - Institut de Recherche Technologique b-com
2 INSA Rennes - Institut National des Sciences Appliquées - Rennes
3 IETR - Institut d'Électronique et des Technologies du numéRique

Channel charting is an unsupervised learning method that aims at mapping wireless channels to a so-called chart, preserving as much as possible spatial neighborhoods. In this paper, a model-based deep learning approach to this problem is proposed. It builds on a physically motivated distance measure to structure and initialize a neural network that is subsequently trained using a triplet loss function. The proposed structure exhibits a low number of parameters and clever initialization leads to fast training. These two features make the proposed approach amenable to on-the-fly channel charting. The method is empirically assessed on realistic synthetic channels, yielding encouraging results.

Mots clés: channel charting; triplet network; dimensionality reduction; MIMO signal processing; machine learning

Domaines: Intelligence artificielle [cs.AI]; Traitement du signal et de l'image [eess.SP]; Réseaux et télécommunications [cs.NI]; Apprentissage [cs.LG]

Taha Yassine, Luc Le Magoarou, Stéphane Paquelet, Matthieu Crussière. Leveraging triplet loss and nonlinear dimensionality reduction for on-the-fly channel charting. 2022. ⟨hal-03629210v2⟩