8000 siomvas (Vasilis Siomos) · GitHub
[go: up one dir, main page]

Skip to content
View siomvas's full-sized avatar

Block or report siomvas

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
siomvas/README.md

Vasilis Siomos

I work on federated learning for medical imaging: how to simulate the heterogeneity of real federations, which architectures train well under it, and how to aggregate under it. AI Scientist at Ultromics and doctoral researcher at City St George's, University of London.

Project Paper Code and models
FDS: Federated Dataset Simulation NeurIPS 2026, Evaluations and Datasets Track (arXiv) fds
ANFR: Adaptive Normalization-Free Feature Recalibration TMLR 2025 (arXiv) ANFR, models on Hugging Face
FedCLAM: Client Adaptive Momentum with Foreground Intensity Matching MICCAI 2025 (arXiv) FedCLAM
ARIA: architectures, initialization and aggregation in federated visual classification ISBI 2024 (arXiv) ARIA
FedChest: a four-client chest X-ray federation used in ANFR FedChest

LinkedIn · Hugging Face

Pinned Loading

  1. awesome-federated-reinforcement-learning awesome-federated-reinforcement-learning Public

    Publication catalog for research on Federated RL (FRL).

    86 10

  2. FDS FDS Public

    FDS: Federated Dataset Simulation. Turn a centralized dataset into a federated benchmark with label-free, controllable heterogeneity, for classification, segmentation and detection. NeurIPS 2026 Ev…

    Python

  3. FedCLAM FedCLAM Public

    PyTorch implementation of FedCLAM: Client Adaptive Momentum with Foreground Intensity Matching for Federated Medical Image Segmentation, accepted at MICCAI 2025

    Python 3

  4. ANFR ANFR Public

    ANFR (TMLR 2025): Adaptive Normalization-free Feature Recalibration, an architecture built for federated learning under data heterogeneity. Code, experiments and ImageNet pre-trained models (timm, …

    Python

  5. ARIA ARIA Public

    ARIA: a benchmark of architectures, initialization (ImageNet, self-supervised) and aggregation methods for federated learning on medical images, built on NVIDIA FLARE. IEEE ISBI 2024.

    Python

  6. FedChest FedChest Public

    Repository for the FedChest dataset

    Python

0