Convolutional Monge Mapping Normalization for learning on sleep data - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Convolutional Monge Mapping Normalization for learning on sleep data

Abstract

In many machine learning applications on signals and biomedical data, especially electroencephalogram (EEG), one major challenge is the variability of the data across subjects, sessions, and hardware devices. In this work, we propose a new method called Convolutional Monge Mapping Normalization (CMMN), which consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. CMMN relies on novel closed-form solutions for optimal transport mappings and barycenters and provides individual test time adaptation to new data without needing to retrain a prediction model. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture when adapting between subjects, sessions, and even datasets collected with different hardware. Notably our performance gain is on par with much more numerically intensive Domain Adaptation (DA) methods and can be used in conjunction with those for even better performances.
Fichier principal
Vignette du fichier
2305.18831.pdf (1.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04359792 , version 1 (21-12-2023)

Licence

Attribution

Identifiers

Cite

Theo Gnassounou, Rémi Flamary, Alexandre Gramfort. Convolutional Monge Mapping Normalization for learning on sleep data. NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, Nouvelle Orléans, United States. ⟨hal-04359792⟩
71 View
64 Download

Altmetric

Share

Gmail Facebook X LinkedIn More