Westlake-AI/SemiReward
[ICLR 2024] SemiReward: A General Reward Model for Semi-supervised Learning
When training machine learning models with limited labeled data and abundant unlabeled data, SemiReward helps you automatically identify and use the most reliable unlabeled examples to improve your model. It takes your existing semi-supervised learning setup and predicts a "reward score" for each unlabeled data point, allowing you to filter out less reliable data. This is useful for researchers and practitioners building models across computer vision, natural language processing, and audio tasks.
Use this if you are working with semi-supervised learning and need a general way to improve the quality of pseudo-labels, especially across diverse tasks and data types.
Not ideal if you already have fully labeled datasets or are using a different learning paradigm than semi-supervised learning with pseudo-labeling.
Stars
77
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Westlake-AI/SemiReward"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification