WesleyHsieh0806/C3-SL
C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning (IEEE MLSP 2022)
This project helps machine learning engineers and researchers accelerate distributed model training, specifically in 'split learning' scenarios. It takes your standard image classification datasets (like CIFAR-10/100) and neural network models and significantly reduces the communication and computation resources needed during training. The outcome is faster training for large models or datasets across different computational environments, without sacrificing accuracy.
No commits in the last 6 months.
Use this if you are performing distributed deep learning training, particularly split learning, and want to drastically reduce the memory and computational overhead.
Not ideal if you are doing local, single-machine model training or working with non-image classification tasks.
Stars
70
Forks
3
Language
Python
License
—
Category
Last pushed
Aug 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/WesleyHsieh0806/C3-SL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)