PDE-Driven Spatiotemporal Disentanglement
Résumé
A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory. Following this direction, we propose in this article a novel and general paradigm for this task based on a resolution method for partial differential equations: the separation of variables. This inspiration allows us to introduce a dynamical interpretation of spatiotemporal disentanglement. It induces a principled model based on learning disentangled spatial and temporal representations of a phenomenon to accurately predict future observations. We experimentally demonstrate the performance and broad applicability of our method against prior state-of-the-art models on physical and synthetic video datasets.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |
![]()
Décrit hal-02911067 Objet présenté à une conférence Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari. PDE-Driven Spatiotemporal Disentanglement. The Ninth International Conference on Learning Representations, International Conference on Representation Learning, May 2021, Vienne, Austria. ⟨hal-02911067v3⟩