tongnie/ImputeFormer

[KDD 2024] "ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation"

31
/ 100
Emerging

This project helps operations engineers, city planners, and environmental scientists accurately fill in missing values in their location-based time series data, such as traffic sensor readings or air quality measurements. You input spatiotemporal datasets with gaps, and it outputs a more complete, reconstructed dataset that balances smoothness with detail, giving you reliable information to analyze.

No commits in the last 6 months.

Use this if you need to accurately fill in missing data points within your spatiotemporal datasets to ensure consistent and reliable analysis.

Not ideal if your data doesn't have both spatial and temporal components, or if you only need very basic missing value imputation.

spatiotemporal-data traffic-monitoring environmental-sensing sensor-data-analysis data-completeness
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

51

Forks

2

Language

Python

License

MIT

Last pushed

May 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tongnie/ImputeFormer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.