Continuous Spatiotemporal Transformers

• URL: http://arxiv.org/abs/2301.13338v2
• Date: Fri, 28 Jul 2023 21:38:47 GMT
• Title: Continuous Spatiotemporal Transformers
• Authors: Antonio H. de O. Fonseca, Emanuele Zappala, Josue Ortega Caro, David van Dijk
• Abstract summary: We present the Continuous Stemporal Transformer (CST), a new transformer architecture that is designed to modeling continuous systems. This new framework guarantees a continuous representation and output via optimization in Sobolev space. We benchmark CST against traditional transformers as well as other smoothtemporal dynamics modeling methods and achieve superior performance in a number of tasks on synthetic and real systems.
• Score: 2.485182034310304
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Modeling spatiotemporal dynamical systems is a fundamental challenge in machine learning. Transformer models have been very successful in NLP and computer vision where they provide interpretable representations of data. However, a limitation of transformers in modeling continuous dynamical systems is that they are fundamentally discrete time and space models and thus have no guarantees regarding continuous sampling. To address this challenge, we present the Continuous Spatiotemporal Transformer (CST), a new transformer architecture that is designed for the modeling of continuous systems. This new framework guarantees a continuous and smooth output via optimization in Sobolev space. We benchmark CST against traditional transformers as well as other spatiotemporal dynamics modeling methods and achieve superior performance in a number of tasks on synthetic and real systems, including learning brain dynamics from calcium imaging data.

Related papers

• Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series [14.400596021890863]
  Many real-world datasets, such as healthcare, climate, and economics, are often collected as irregular time series. We propose the Amortized Control of continuous State Space Model (ACSSM) for continuous dynamical modeling of time series.
  arXiv  Detail & Related papers  (2024-10-08T01:27:46Z)
• 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)
• QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning [17.914580097058106]
  We investigate the use of Transformers in Reinforcement Learning (RL) We learn an autoregressive discrete Q-function using a separate Q-Transformer model to estimate a long-term return beyond the short-horizon planning. Our proposed method, QT-TDM, integrates the robust predictive capabilities of Transformers as dynamics models with the efficacy of a model-free Q-Transformer to mitigate the computational burden associated with real-time planning.
  arXiv  Detail & Related papers  (2024-07-26T16:05:26Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling [30.12824131306359]
  Modeling continuous-time dynamics on irregular time series is critical to account for data evolution and correlations that occur continuously. Traditional methods including recurrent neural networks or Transformer models leverage inductive bias via powerful neural architectures to capture complex patterns. We propose ContiFormer that extends the relation modeling of vanilla Transformer to the continuous-time domain.
  arXiv  Detail & Related papers  (2024-02-16T12:34:38Z)
• Convolutional State Space Models for Long-Range Spatiotemporal Modeling [65.0993000439043]
  ConvS5 is an efficient variant for long-rangetemporal modeling. It significantly outperforms Transformers and ConvNISTTM on a long horizon Moving-Lab experiment while training 3X faster than ConvLSTM and generating samples 400X faster than Transformers.
  arXiv  Detail & Related papers  (2023-10-30T16:11:06Z)
• Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems [14.553972457854517]
  We present a data-driven, space-time continuous framework to learn surrogatemodels for complex physical systems. We leverage the expressive power of the network and aspecially designed consistency-inducing regularization to obtain latent trajectories that are both low-dimensional and smooth.
  arXiv  Detail & Related papers  (2023-01-25T03:06:03Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Learning stochastic dynamics and predicting emergent behavior using transformers [0.0]
  We show that a neural network can learn the dynamical rules of a system by observation of a single dynamical trajectory of the system. We train a neural network called a transformer on a single trajectory of the model. Transformers have the flexibility to learn dynamical rules from observation without explicit enumeration of rates or coarse-graining of configuration space.
  arXiv  Detail & Related papers  (2022-02-17T15:27:21Z)
• Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation [91.05073136215886]
  "Actor-Learner Distillation" transfers learning progress from a large capacity learner model to a small capacity actor model. We demonstrate in several challenging memory environments that using Actor-Learner Distillation recovers the clear sample-efficiency gains of the transformer learner model.
  arXiv  Detail & Related papers  (2021-04-04T17:56:34Z)

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.