zhouhaoyi/Informer2020
The GitHub repository for the paper "Informer" accepted by AAAI 2021.
Introduces ProbSparse Attention, a sparse attention mechanism that selectively attends to "active" queries based on probability distributions rather than computing full attention matrices, reducing complexity for long sequences. Built in PyTorch with support for multivariate time-series forecasting across multiple datasets (ETT, ECL, Weather) via configurable encoder-decoder architecture with optional distillation and mixed-precision training. Includes Docker-based reproducibility setup and Colab notebooks for experiments on custom data.
6,440 stars. No commits in the last 6 months.
Stars
6,440
Forks
1,286
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zhouhaoyi/Informer2020"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
aeon-toolkit/aeon
A toolkit for time series machine learning and deep learning
sktime/sktime
A unified framework for machine learning with time series
skforecast/skforecast
Time series forecasting with machine learning models
Nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
Nixtla/mlforecast
Scalable machine 🤖 learning for time series forecasting.