TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Neural Ordinary Differential Equations

Neural Ordinary Differential Equations

Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud

2018-06-19NeurIPS 2018 12Multivariate Time Series ImputationPose EstimationMultivariate Time Series Forecasting
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCode(official)Code

Abstract

We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, we show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models.

Results

TaskDatasetMetricValueModel
ImputationPhysioNet Challenge 2012mse (10^-3)3.907Latent ODE (RNN enc.)
ImputationPhysioNet Challenge 2012mse (10^-3)5.93RNN-VAE
ImputationMuJoCoMSE (10^2, 50% missing)0.447Latent ODE (RNN enc.)
ImputationMuJoCoMSE (10^2, 50% missing)6.1RNN-VAE
Time Series ForecastingMuJoCoMSE (10^-2, 50% missing)1.377Latent ODE (RNN enc.)
Time Series ForecastingMuJoCoMSE (10^-2, 50% missing)1.782RNN-VAE
Time Series ForecastingUSHCN-DailyMSE0.83NeuralODE-VAE-Mask
Time Series ForecastingUSHCN-DailyMSE0.96NeuralODE-VAE
Time Series ForecastingPhysioNet Challenge 2012MSE stdev0.145RNN-VAE
Time Series ForecastingPhysioNet Challenge 2012mse (10^-3)3.055RNN-VAE
Time Series ForecastingPhysioNet Challenge 2012MSE stdev0.052Latent ODE (RNN enc.)
Time Series ForecastingPhysioNet Challenge 2012mse (10^-3)3.162Latent ODE (RNN enc.)
Feature EngineeringPhysioNet Challenge 2012mse (10^-3)3.907Latent ODE (RNN enc.)
Feature EngineeringPhysioNet Challenge 2012mse (10^-3)5.93RNN-VAE
Feature EngineeringMuJoCoMSE (10^2, 50% missing)0.447Latent ODE (RNN enc.)
Feature EngineeringMuJoCoMSE (10^2, 50% missing)6.1RNN-VAE
Time Series AnalysisMuJoCoMSE (10^-2, 50% missing)1.377Latent ODE (RNN enc.)
Time Series AnalysisMuJoCoMSE (10^-2, 50% missing)1.782RNN-VAE
Time Series AnalysisUSHCN-DailyMSE0.83NeuralODE-VAE-Mask
Time Series AnalysisUSHCN-DailyMSE0.96NeuralODE-VAE
Time Series AnalysisPhysioNet Challenge 2012MSE stdev0.145RNN-VAE
Time Series AnalysisPhysioNet Challenge 2012mse (10^-3)3.055RNN-VAE
Time Series AnalysisPhysioNet Challenge 2012MSE stdev0.052Latent ODE (RNN enc.)
Time Series AnalysisPhysioNet Challenge 2012mse (10^-3)3.162Latent ODE (RNN enc.)
Multivariate Time Series ForecastingMuJoCoMSE (10^-2, 50% missing)1.377Latent ODE (RNN enc.)
Multivariate Time Series ForecastingMuJoCoMSE (10^-2, 50% missing)1.782RNN-VAE
Multivariate Time Series ForecastingUSHCN-DailyMSE0.83NeuralODE-VAE-Mask
Multivariate Time Series ForecastingUSHCN-DailyMSE0.96NeuralODE-VAE
Multivariate Time Series ForecastingPhysioNet Challenge 2012MSE stdev0.145RNN-VAE
Multivariate Time Series ForecastingPhysioNet Challenge 2012mse (10^-3)3.055RNN-VAE
Multivariate Time Series ForecastingPhysioNet Challenge 2012MSE stdev0.052Latent ODE (RNN enc.)
Multivariate Time Series ForecastingPhysioNet Challenge 2012mse (10^-3)3.162Latent ODE (RNN enc.)

Related Papers

$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning2025-07-17Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark2025-07-17DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model2025-07-17From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation2025-07-17AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability2025-07-17SpatialTrackerV2: 3D Point Tracking Made Easy2025-07-16SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation2025-07-16Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation2025-07-16