diffdist
by ag14774
AI summary
Distributed Backpropagation Library
Enables backpropagation in distributed settings and facilitates model parallelism using differentiable communication between processes
- stars
- 62
- forks
- 6
- watching
- 1
Similar projects
Found by comparing what the projects do, not just their names.
Backprop algorithm library
A Haskell library providing automatic heterogeneous back-propagation for differentiable programming and deep learning applications.
Sorting library
A library that allows gradients to be propagated through sorting operations, enabling differentiable sorting networks.
Federated learning library
An implementation of federated learning with prototype-based methods across heterogeneous clients
DPFL Algorithm
This repository provides an implementation of a differentially private federated learning algorithm designed to improve the robustness and performance of federated machine learning systems.
Parallel data processor
A Haskell-based framework for processing and distributing large datasets across multiple nodes in parallel.
Pseudo labeling
A PyTorch implementation of a method for improving semi-supervised learning in federated settings by adapting pseudo labels to balance classes.
Model distiller
Automatically trains models from large foundation models to perform specific tasks with minimal human intervention.
Domain generalization method
This project presents a method for federated domain generalization with adjustment, allowing multiple models to learn from each other across different domains.
Federated Learning Library
An implementation of Personalized Federated Learning with Gaussian Processes using Python.
JSON diff library
A Scala library for computing diffs and patches of JSON data
Federated Learning Library
An implementation of federated learning with sparse training and readjustment mechanisms to reduce communication overhead while maintaining model performance.
Process runner
A library for managing subprocesses in Python.
Region-of-Interest Training
Training and deploying large language models on computer vision tasks using region-of-interest inputs
Federated Learning
This project enables personalized federated learning with inferred collaboration graphs to improve the performance of machine learning models on non-IID (non-independent and identically distributed) datasets.
Federated Learning Reverser
An algorithm that breaks secure aggregation protocols in federated learning by recovering individual model updates from aggregated sums
