https://github.com/patrick-kidger/NeuralCDE

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)
https://github.com/patrick-kidger/NeuralCDE

controlled-differential-equations deep-learning deep-neural-networks differential-equations dynamical-systems machine-learning neural-differential-equations neural-networks pytorch rough-paths time-series

Last synced: 3 days ago
JSON representation

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

• Host: GitHub
• URL: https://github.com/patrick-kidger/NeuralCDE
• Owner: patrick-kidger
• License: apache-2.0
• Created: 2020-05-18T12:00:22.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-10-22T13:32:29.000Z (about 2 years ago)
• Last Synced: 2024-10-17T10:06:46.977Z (19 days ago)
• Topics: controlled-differential-equations, deep-learning, deep-neural-networks, differential-equations, dynamical-systems, machine-learning, neural-differential-equations, neural-networks, pytorch, rough-paths, time-series
• Language: Python
• Homepage:
• Size: 615 KB
• Stars: 618
• Watchers: 20
• Forks: 67
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-time-series - [Code

README

        
 Neural Controlled Differential Equations for Irregular Time Series
(NeurIPS 2020 Spotlight)


    [arXiv, YouTube] 








Building on the well-understood mathematical theory of _controlled differential equations_, we demonstrate how to construct models that:

+ Act directly on irregularly-sampled partially-observed multivariate time series.

+ May be trained with memory-efficient adjoint backpropagation - even across observations.

+ Demonstrate state-of-the-art performance.

They are straightforward to implement and evaluate using existing tools, in particular PyTorch and the [`torchcde`](https://github.com/patrick-kidger/torchcde) library.

----

### Library

See [`torchcde`](https://github.com/patrick-kidger/torchcde).

### Example

We encourage looking at [example.py](https://github.com/patrick-kidger/torchcde/blob/master/example/example.py), which demonstrates how to use the library to train a Neural CDE model to predict the chirality of a spiral.

Also see [irregular_data.py](https://github.com/patrick-kidger/torchcde/blob/master/example/irregular_data.py), for demonstrations on how to handle variable-length inputs, irregular sampling, or missing data, all of which can be handled easily, without changing the model.

A self contained short example:

```python

import torch

import torchcde

# Create some data

batch, length, input_channels = 1, 10, 2

hidden_channels = 3

t = torch.linspace(0, 1, length)

t_ = t.unsqueeze(0).unsqueeze(-1).expand(batch, length, 1)

x_ = torch.rand(batch, length, input_channels - 1)

x = torch.cat([t_, x_], dim=2)  # include time as a channel

# Interpolate it

coeffs = torchcde.natural_cubic_spline_coeffs(x)

X = torchcde.NaturalCubicSpline(coeffs)

# Create the Neural CDE system

class F(torch.nn.Module):

    def __init__(self):

        super(F, self).__init__()

        self.linear = torch.nn.Linear(hidden_channels, 

                                      hidden_channels * input_channels)

    def forward(self, t, z):

        return self.linear(z).view(batch, hidden_channels, input_channels)

func = F()

z0 = torch.rand(batch, hidden_channels)

# Integrate it

torchcde.cdeint(X=X, func=func, z0=z0, t=X.interval)

```







### Reproducing experiments

Everything to reproduce the experiments of the paper can be found in the [`experiments` folder](./experiments). Check the folder for details.

### Results

As an example (taken from the paper - have a look there for similar results on other datasets):







### Citation

```bibtex

@article{kidger2020neuralcde,

    title={{N}eural {C}ontrolled {D}ifferential {E}quations for {I}rregular {T}ime {S}eries},

    author={Kidger, Patrick and Morrill, James and Foster, James and Lyons, Terry},

    journal={Advances in Neural Information Processing Systems},

    year={2020}

}

```