mit-gfx/ContinuousParetoMTL

[ICML 2020] Efficient Continuous Pareto Exploration in Multi-Task Learning

37
/ 100
Emerging

When training machine learning models to perform multiple tasks simultaneously, it's common to face trade-offs where improving one task degrades another. This project helps you efficiently find the best possible balance across these tasks. You provide your multi-task dataset and model, and it outputs a range of optimized models, each representing a different effective trade-off. This is ideal for machine learning practitioners and researchers working on real-world multi-objective optimization problems.

149 stars. No commits in the last 6 months.

Use this if you need to train a single model that performs well across multiple, potentially conflicting, objectives and want to explore the optimal compromises.

Not ideal if your model only has a single objective, or if you are not comfortable working with command-line tools and Python scripting for machine learning.

multi-task learning model optimization Pareto optimization machine learning research model balancing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

149

Forks

26

Language

Jupyter Notebook

License

Last pushed

Aug 12, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mit-gfx/ContinuousParetoMTL"

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