ZLiu21/SoftShape

This is an official pytorch implementation for paper "Learning Soft Sparse Shapes for Efficient Time-Series Classification" (ICML-25, Spotlight).

33
/ 100
Emerging

This project helps researchers and data scientists classify time series data more efficiently and with clearer explanations. It takes your time series datasets and identifies key patterns (or "shapes") within them, providing highly accurate classifications along with interpretable insights into why a particular classification was made. It's designed for anyone working with sequential data who needs to understand the underlying drivers of classification outcomes.

No commits in the last 6 months.

Use this if you need to classify complex time series data and require both high accuracy and clear interpretability for your results.

Not ideal if your primary goal is simple classification without any need for understanding the contributing patterns or shapes.

time-series-analysis pattern-recognition data-science predictive-modeling interpretable-AI
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 18 / 25

How are scores calculated?

Stars

20

Forks

12

Language

Python

License

Last pushed

Jun 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZLiu21/SoftShape"

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