surgicalaggregation
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: BioIntelligence-Lab
- License: gpl-3.0
- Language: Python
- Default Branch: main
- Size: 43 KB
Statistics
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
NOTE: This repository is currently work in progress.
Machine Learning for Health 2024
We are excited to announce that our paper has been accepted for proceedings track at 2024 Machine Learning for Health Symposium in Vancouver!
From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification
Pranav Kulkarni, Adway kanhere, Paul H. Yi, Vishwa S. Parekh
Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collaboratively train a global model using distributed, class-heterogeneous datasets. Unlike other methods, our method does not rely on the assumption that clients share the same classes as other clients, know the classes of other clients, or have access to a fully annotated dataset. We evaluate surgical aggregation using class-heterogeneous CXR datasets across IID and non-IID settings. Our results show that our method outperforms current methods and has better generalizability.
Read the full paper here.
Owner
- Name: BioIntelligence-Lab
- Login: BioIntelligence-Lab
- Kind: organization
- Repositories: 1
- Profile: https://github.com/BioIntelligence-Lab
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: Surgical Aggregation
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Pranav
family-names: Kulkarni
email: pkulkarni@som.umaryland.edu
- given-names: Adway
family-names: Kanhere
email: akanhere@som.umaryland.edu
- given-names: Paul H.
family-names: Yi
email: pyi@som.umaryland.edu
- given-names: Vishwa S.
family-names: Parekh
email: vparekh@som.umaryland.edu
identifiers:
- type: doi
value: 10.48550/arXiv.2301.06683
repository-code: 'https://github.com/UM2ii/SurgicalAggregation'
license: GPL-3.0
GitHub Events
Total
- Watch event: 1
- Push event: 1
Last Year
- Watch event: 1
- Push event: 1