Reproduce “FedMRL: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning for Medical Imaging” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Pranab Sahoo, Ashutosh Tripathi, Sriparna Saha, Samrat Mondal
FedMRL addresses heterogeneous medical image learning across hospitals without pooling patient images. It combines locally adjusted training, a fairness-motivated loss term, adaptive proximal regularization, and self-organizing-map aggregation coordinated by server-side agents. On two datasets under severe heterogeneity, it reports the highest displayed accuracy and F1. On Messidor, accuracy is 57.91 versus FedProx’s 57.08, without ablations or hospital-level fairness results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.