Skip to content

Commit 4323e00

Browse files
committed
updated readme and added images
1 parent 79c7ee1 commit 4323e00

File tree

4 files changed

+34
-14
lines changed

4 files changed

+34
-14
lines changed

README.md

Lines changed: 34 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -1,21 +1,17 @@
11
# Interpolation-Prediction Networks
2-
In this work, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time
3-
series. The architecture is based on the use of a semi-parametric interpolation
4-
network followed by the application of a prediction network. The interpolation
5-
network allows for information to be shared across multiple dimensions of a multivariate time series during the interpolation stage, while any standard deep learning model can be used for the prediction network.
6-
7-
We use a two layer interpolation network. The first interpolation layer performs a semi-parametric univariate interpolation for each of the D time series separately while the second layer merges information from across all of the D time series at each reference time point by taking into account the correlations among the time series.
8-
9-
10-
## Reference
11-
> Satya Narayan Shukla and Benjamin Marlin. Interpolation-prediction networks for irregularly sampled time series. In International Conference on Learning Representations, 2019. \[[pdf](https://openreview.net/pdf?id=r1efr3C9Ym)\]
12-
2+
This repository is an official implementation of [Interpolation-Prediction Networks for Irregularly Sampled Time Series](https://openreview.net/pdf?id=r1efr3C9Ym), accepted at ICLR 2019. In this work, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series.
3+
<p align="center">
4+
<img width="600" src="imgs/model.png">
5+
</p>
136

147
## Requirements
158
The code requires Python 3.7 or later. The file [requirements.txt](requirements.txt) contains the full list of
169
required Python modules.
10+
```bash
11+
pip install -r requirements.txt
12+
```
1713

18-
## Usage
14+
## Training and Evaluation
1915
For running our model on univariate time series (UWave dataset):
2016
```bash
2117
python src/univariate_example.py --epochs 1000 --hidden_units 2048 --ref_points 128 --batch_size 2048
@@ -29,8 +25,32 @@ Once the database has been created, run these scripts in order.
2925
python src/mimic_data_extraction.py
3026
python src/multivariate_example.py --epochs 1000 --reference_points 192 --hours_from_adm 48 --batch_size 256 --gpus 4
3127
```
32-
### Data Format Example
33-
The notations here align with the notation section 3.1 in the paper. For brevity, lets assume we have just one example in the training set and dimension `d = 2`. ![Input format example](dataformat.png)
28+
29+
## Results
30+
Classification and regression performance on MIMIC-III.
31+
<p align="center">
32+
<img width="600" src="imgs/results.png">
33+
</p>
34+
35+
## Data Format Example
36+
The notations here align with the notation section 3.1 in the paper. For brevity, lets assume we have just one example in the training set and dimension `d = 2`.
37+
<p align="center">
38+
<img width="600" src="imgs/dataformat.png">
39+
</p>
40+
41+
## Reference
42+
```bash
43+
@inproceedings{
44+
shukla2018interpolationprediction,
45+
title={Interpolation-Prediction Networks for Irregularly Sampled Time Series},
46+
author={Satya Narayan Shukla and Benjamin Marlin},
47+
booktitle={International Conference on Learning Representations},
48+
year={2019},
49+
url={https://openreview.net/forum?id=r1efr3C9Ym},
50+
}
51+
```
3452

3553
## Contact
3654
For more details, please contact <snshukla@cs.umass.edu>.
55+
56+
File renamed without changes.

imgs/model.png

436 KB
Loading

imgs/results.png

832 KB
Loading

0 commit comments

Comments
 (0)