HarmoFL
Drift harmonizer
A framework to harmonize local and global drifts in federated learning on heterogeneous medical images
[AAAI'22] HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images
85 stars
4 watching
16 forks
Language: Python
last commit: over 2 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| med-air/fedbn | An approach to federated learning that addresses feature shift non-iid by normalizing local batch features before averaging models. | 231 |
 mmendiet/fedalign | A federated learning framework designed to mitigate data heterogeneity in distributed learning settings. | 55 |
 garyzhang99/dm-pfl | A framework for personalized federated learning that improves shift-robustness with minimal extra training overhead | 3 |
 ymjs-irfan/dp-fedsam | This repository provides an implementation of a differentially private federated learning algorithm designed to improve the robustness and performance of federated machine learning systems. | 41 |
 gaoliang13/feddc | Federated learning algorithm that adapts to non-IID data by decoupling and correcting for local drift | 79 |
 ifca-advanced-computing/frouros | A Python library that detects drifts in machine learning systems | 193 |
 diaoenmao/heterofl-computation-and-communication-efficient-federated-learning-for-heterogeneous-clients | An implementation of efficient federated learning algorithms for heterogeneous clients | 152 |
 hyhmia/distrans | Improves federated learning models by addressing data heterogeneity through distributional transformation | 5 |
 diogenes0319/fedmd_clean | An implementation of a heterogenous federated learning framework using model distillation. | 149 |
 liuquande/feddg-elcfs | A framework for federated learning on medical image segmentation using continuous frequency space interpolation. | 240 |
 hypervoyager/pfl | An implementation of heterogeneous federated learning with parallel edge and server computation | 16 |
 haozhaowang/dafkd2023 | A framework for achieving domain-aware knowledge distillation in federated learning environments. | 26 |
 yuqifan1117/hallucidoctor | This project provides tools and frameworks to mitigate hallucinatory toxicity in visual instruction data, allowing researchers to fine-tune MLLM models on specific datasets. | 41 |
 ag14774/diffdist | Enables backpropagation in distributed settings and facilitates model parallelism using differentiable communication between processes | 61 |
 hackergrrl/ipfs-hyperlog | A Merkle DAG implementation for replicating immutable data in a peer-to-peer network | 57 |