Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Awesome Deep Learning for Time-Series Imputation, including an unmissable paper and tool list about applying neural networks to impute incomplete time series containing NaN missing values/data
| Date | Stars |
|---|---|
| 2026-07-31 | 423 |
| 2026-08-03 | 423 |
| 2026-08-05 | 423 |
| 2026-08-06 | 423 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<a id="AwesomeImputation" href="#AwesomeImputation">
<img src="https://pypots.com/figs/pypots_logos/AwesomeImputation/banner.jpg"
alt="Time Series Imputation Survey and Benchmark"
title="Time Series Imputation Survey and Benchmark"
width="80%"
/>
</a>
</p>
The repository for the paper [**TSI-Bench: Benchmarking Time Series Imputation**](https://arxiv.org/abs/2406.12747)
from <a href="https://pypots.com" target="_blank"><img src="https://pypots.com/figs/pypots_logos/PyPOTS/logo_FFBG.svg" width="30px" align="center"/> PyPOTS Research</a>.
The code and configurations for reproducing the experimental results in the paper are available under the folder `benchmark_code`.
The README file here maintains a list of must-read papers on time-series imputation, and a collection of time-series imputation toolkits and resources.
🤗 Contributions to update new resources and articles are very welcome!
## ❖ Time-Series Imputation Toolkits
### `Datasets`
[TSDB (Time Series Data Beans)](https://github.com/WenjieDu/TSDB): a Python toolkit loads 172 public time-series datasets with a single line of code.
<img src="https://img.shields.io/github/last-commit/WenjieDu/TSDB" align="center">
[BenchPOTS](https://github.com/WenjieDu/BenchPOTS): a Python suite provides standard preprocessing pipelines of 170 public datasets for benchmarking machine learning on POTS (Partially-Observed Time Series).
<img src="https://img.shields.io/github/last-commit/WenjieDu/BenchPOTS" align="center">
### `Missingness`
[PyGrinder](https://github.com/WenjieDu/PyGrinder): a Python library grinds data beans into the incomplete by introducing missing values with different missing patterns.
<img src="https://img.shields.io/github/last-commit/WenjieDu/PyGrinder" align="center">
### `Algorithms`
[PyPOTS](https://github.com/WenjieDu/PyPOTS): a Python toolbox for machine learning on POTS (Partially-Observed Time Series)
<img src="https://img.shields.io/github/last-commit/WenjieDu/PyPOTS" align="center">
[MICE](https://github.com/amices/mice): Multivariate Imputation by Chained Equations
<img src="https://img.shields.io/github/last-commit/amices/mice" align="center">
[AutoImpute](https://github.com/kearnz/autoimpute): a Python package for Imputation Methods
<img src="https://img.shields.io/github/last-commit/kearnz/autoimpute" align="center">
[Impyute](https://github.com/eltonlaw/impyute): a library of missing data imputation algorithms
<img src="https://img.shields.io/github/last-commit/eltonlaw/impyute" align="center">
## ❖ Must-Read Papers on Time-Series Imputation
The papers listed here may be not from top publications, some of them even are not deep-learning methods,
but are all interesting papers related to time-series imputation that deserve reading to
researchers and practitioners who are interested in this field.
Paper link and official code link are provided if available.
Logo <img src="https://pypots.com/figs/pypots_logos/PyPOTS/logo_FFBG.svg" width="26px" align="center"/> indicates that if the model has been validated and integrated into [PyPOTS](https://github.com/WenjieDu/PyPOTS) for easy usage.
### `Year 2025`
[IJCAI] **Deep Learning for Multivariate Time Series Imputation: A Survey**
[[paper](https://arxiv.org/pdf/2402.04059)]
[ICLR] **TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis**
[[paper](https://openreview.net/forum?id=1CLzLXSFNn)]
[[~~official code~~](https://anonymous.4open.science/r/TimeMixerPP-4F2A) (expired)]
[<img src="https://pypots.com/figs/pypots_logos/PyPOTS/logo_FFBG.svg" width="26px" align="center"/>](https://github.com/WenjieDu/PyPOTS?tab=readme-ov-file#-available-algorithms)
[ICLR] **Optimal Transport for Time Series Imputation**
[[paper](https://openreview.net/forum?id=xPTzjpIQNp)]
[[official code](https://github.com/FMLYD/PSW-I)]
### `Year 2024`
[TMLR] **TOTEM: Tokenized Time Series Embeddings for General Time SeExcerpt of 19,311 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8078b14c25b1e6ab, topic:deep-learning, topic:neural-network
matched fp:8078b14c25b1e6ab, topic:benchmark