CRIBIER-DELANDE Perrine
Supervision : Ludovic DENOYER
Co-supervision : GUIGUE Vincent
Contexts and user modelling through disentangled representations learning
The recent, sometimes very publicised, successes have drawn a lot of attention to Deep Learning (DL). Many questions are asked about the limitations of these techniques. The great strength of DL is its ability to learn representations of complex objects. Renault, as a car manufacturer, has a vested interest in discovering how their cars are used. Learning representations of drivers is one of their long-term goals. Renault’s strength partly lies in their knowledge of cars and the data they use and produce. This data is almost entirely contained in the Controller Area Network (CAN). However, the CAN data only contains the inner workings of a car and not its surroundings. As many factors exterior to the driver and the car (such as weather, other road users, road condition…) can affect driving, we must find a way to disentangle them. Seeing the user (or driver) as just another context allowed us to use context modelling approaches. By transferring disentanglement approaches used in computer vision, we were able to develop models that learn disentangled representations of contexts. We tested these models with a few public datasets of time series with clearly labelled contexts. Using only forecasting as supervision during training, our models are able to generate data only from the learned representations of contexts. They even learn to represent new contexts, only seen after training. We then transferred the developed models on CAN data and were able to confirm that information about driving contexts (including driver’s identity) is indeed contained in the CAN.
Defence : 04/02/2021
Jury members :
OUKHELLOU Latifa (Directrice de Recherche/ IFSTTAR, GRETTIA) [Rapportrice]
RALAIVOLA Liva (Professeur/ Criteo Research Lab) [Rapporteur]
GALLINARI Patrick (Professeur/ Sorbonne Université, LIP6)
ARTIÈRES Thierry (Professeur/ École Centrale Marseille, LIS)
GUIGUE Vincent (Maitre de Conférence/ Sorbonne Université, LIP6)
DENOYER Ludovic (Professeur/ Facebook Research)
2019-2021 Publications
-
2021
- P. Cribier‑Delande : “Contexts and user modelling through disentangled representations learning”, thesis, phd defence 04/02/2021, supervision Denoyer, Ludovic, co-supervision : Guigue, Vincent (2021)
-
2020
- P. Cribier‑Delande, R. Puget, V. Guigue, L. Denoyer : “Time Series Prediction using Disentangled Latent Factors”, ESANN 2020 - 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium (2020)
-
2019
- V. Guiguet, P. Cribier‑Delande, N. Baskiotis, V. Guigue : “PrĂ©diction de sĂ©ries temporelles multi-variĂ©es stationnaires: modĂ©lisation du contexte pour l’analyse des donnĂ©es de transports”, GRETSI 2019, Lille, France (2019)