YujiaBao/ls
Learning to Split for Automatic Bias Detection
This tool helps machine learning practitioners identify hidden biases within their datasets. By automatically splitting your dataset, it reveals subsets where models fail, even if they perform well on the training data. The output is a challenging train/test split that highlights specific data points causing generalization issues, helping you debug and build more robust models.
No commits in the last 6 months.
Use this if you need to find out why your machine learning model isn't performing well on new, unseen data, or suspect hidden biases are causing poor generalization.
Not ideal if you're looking for a general-purpose data splitting utility without a focus on bias detection or if you are not working with PyTorch datasets and models.
Stars
47
Forks
7
Language
Python
License
MIT
Category
Last pushed
May 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YujiaBao/ls"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/scaaml
SCAAML: Side Channel Attacks Assisted with Machine Learning
pralab/secml
A Python library for Secure and Explainable Machine Learning
Koukyosyumei/AIJack
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
AI-SDC/SACRO-ML
Collection of tools and resources for managing the statistical disclosure control of trained...
oss-slu/mithridatium
Mithridatium is a research-driven project aimed at detecting backdoors and data poisoning in...