YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
This toolkit helps data scientists, machine learning engineers, and researchers efficiently train machine learning models when they have a lot of unlabeled data but only a small amount of labeled data. It takes in various data types like tabular, image, text, or graph data, along with some labeled examples and many unlabeled ones. The output is a trained classification, regression, or clustering model that performs well even with limited labeled input.
210 stars. Available on PyPI.
Use this if you need to build accurate machine learning models but are struggling with high data labeling costs or limited access to pre-labeled datasets.
Not ideal if your dataset is fully labeled or if you are looking for a tool focused solely on unsupervised learning or reinforcement learning.
Stars
210
Forks
16
Language
Python
License
MIT
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YGZWQZD/LAMDA-SSL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification
microsoft/Semi-supervised-learning
A Unified Semi-Supervised Learning Codebase (NeurIPS'22)