PDE-Driven Spatiotemporal Disentanglement

• URL: http://arxiv.org/abs/2008.01352v3
• Date: Tue, 23 Mar 2021 09:44:40 GMT
• Title: PDE-Driven Spatiotemporal Disentanglement
• Authors: J\'er\'emie Don\`a (MLIA), Jean-Yves Franceschi (MLIA), Sylvain Lamprier (MLIA), Patrick Gallinari (MLIA)
• Abstract summary: A recent line of work in the machine learning community addresses the problem of predicting high-dimensional phenomena by leveraging tools specific from the differential equations theory. We propose a novel and general paradigm for this task based on a method for partial differential equations: separation of variables. We experimentally demonstrate the performance and broad applicability of our method against prior state-of-the-art models on physical and synthetic video datasets.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Latent Space Energy-based Neural ODEs [73.01344439786524]
  This paper introduces a novel family of deep dynamical models designed to represent continuous-time sequence data. We train the model using maximum likelihood estimation with Markov chain Monte Carlo. Experiments on oscillating systems, videos and real-world state sequences (MuJoCo) illustrate that ODEs with the learnable energy-based prior outperform existing counterparts.
  arXiv  Detail & Related papers  (2024-09-05T18:14:22Z)
• Sequential Representation Learning via Static-Dynamic Conditional Disentanglement [58.19137637859017]
  This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between those factors by explicitly accounting for the causal relationship between the static/dynamic variables. Experiments show that the proposed approach outperforms previous complex state-of-the-art techniques in scenarios where the dynamics of a scene are influenced by its content.
  arXiv  Detail & Related papers  (2024-08-10T17:04:39Z)
• PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations [49.80959046861793]
  We present PDETime, a novel LMTF model inspired by the principles of Neural PDE solvers. Our experimentation across seven diversetemporal real-world LMTF datasets reveals that PDETime adapts effectively to the intrinsic nature of the data.
  arXiv  Detail & Related papers  (2024-02-25T17:39:44Z)
• Course Correcting Koopman Representations [12.517740162118855]
  We study autoencoder formulations of this problem, and different ways they can be used to model dynamics. We propose an inference-time mechanism, which we refer to as Periodic Reencoding, for faithfully capturing long term dynamics.
  arXiv  Detail & Related papers  (2023-10-23T22:36:31Z)
• Discovering Interpretable Physical Models using Symbolic Regression and Discrete Exterior Calculus [55.2480439325792]
  We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models. DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems. We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
  arXiv  Detail & Related papers  (2023-10-10T13:23:05Z)
• Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections [6.345523830122166]
  We propose PolyODE, a formulation that enforces long-range memory and preserves a global representation of the underlying dynamical system. Our construction is backed by favourable theoretical guarantees and we demonstrate that it outperforms previous works in the reconstruction of past and future data.
  arXiv  Detail & Related papers  (2023-03-03T10:49:09Z)
• Semi-supervised Learning of Partial Differential Operators and Dynamical Flows [68.77595310155365]
  We present a novel method that combines a hyper-network solver with a Fourier Neural Operator architecture. We test our method on various time evolution PDEs, including nonlinear fluid flows in one, two, and three spatial dimensions. The results show that the new method improves the learning accuracy at the time point of supervision point, and is able to interpolate and the solutions to any intermediate time.
  arXiv  Detail & Related papers  (2022-07-28T19:59:14Z)
• Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks [2.538209532048867]
  We derive a continuous-time model for the dynamics of the data via the finite element method. The resulting graph neural network estimates the instantaneous effects of the unknown dynamics on each cell in a meshing of the spatial domain. A qualitative analysis shows that our model disentangles the data into their constituent parts, which makes it uniquely interpretable.
  arXiv  Detail & Related papers  (2022-03-16T18:19:43Z)
• Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations [62.81701992551728]
  We present a physics-informed framework for solving time-dependent partial differential equations. Our model utilizes discrete cosine transforms to encode spatial and recurrent neural networks. We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations.
  arXiv  Detail & Related papers  (2022-02-24T20:46:52Z)
• A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data [10.217447098102165]
  We consider the problem of learning prediction models for physical processes driven by unknown partial differential equations (PDEs) We propose a deep learning framework that learns the underlying dynamics and predicts its evolution using sparsely distributed data sites.
  arXiv  Detail & Related papers  (2020-11-30T16:38:00Z)
• Neural Controlled Differential Equations for Irregular Time Series [17.338923885534197]
  An ordinary differential equation is determined by its initial condition, and there is no mechanism for adjusting the trajectory based on subsequent observations. Here we demonstrate how this may be resolved through the well-understood mathematics of emphcontrolled differential equations We show that our model achieves state-of-the-art performance against similar (ODE or RNN based) models in empirical studies on a range of datasets.
  arXiv  Detail & Related papers  (2020-05-18T17:52:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.