ForestsKing/D3R

PyTorch implementation of "Drift doesn't Matter: Dynamic Decomposition with Dffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection" (NeurIPS 2023)

34
/ 100
Emerging

This project helps operations engineers and data analysts detect unusual activity in complex systems where conditions often change. It takes in streams of sensor data or other multivariate time series and outputs signals indicating potential anomalies, even when the system itself is undergoing normal 'drift' or shifts in behavior. This is ideal for monitoring industrial control systems, network performance, or environmental sensors.

No commits in the last 6 months.

Use this if you need to reliably find anomalies in real-time data from systems that naturally evolve or experience changing operational conditions, without getting flooded by false alarms.

Not ideal if your time series data is perfectly stable with no expected shifts over time, or if you only have a single data stream rather than multiple correlated metrics.

operations-monitoring industrial-control-systems sensor-data-analysis predictive-maintenance system-health
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

86

Forks

12

Language

Python

License

Last pushed

Jul 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ForestsKing/D3R"

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