scientific-federated-learning

Coordinate Flower-based federated learning with DP-SGD and non-IID data splits.

3|1|Updated Feb 11, 2026

Search Tags:#privacy-preserving #federated-learning #flower #dp-sgd #non-iid #distributed-ml

Ready to run

npx skills add https://github.com/nahisaho/satori --skill scientific-federated-learning

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scientific-federated-learning
Source: https://github.com/nahisaho/satori/tree/main/src/.github/skills/scientific-federated-learning
Command: npx skills add https://github.com/nahisaho/satori --skill scientific-federated-learning

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Federated learning across multiple organizations to train models without sharing raw data, enabling privacy-preserving collaborative ML.

Core Features & Use Cases

Flower-based FL pipeline with FedAvg/FedProx/FedOpt aggregation strategies
Differential privacy via DP-SGD and support for non-IID data splits
Efficient cross-site coordination and workflow orchestration for scientific data analysis
Use Case: Research institutions and hospitals collaboratively train models without exposing sensitive data.

Quick Start

Launch a Flower-based federated learning pipeline across clients and apply DP-SGD with non-IID data splits to start training.

Frequently Asked Questions about scientific-federated-learning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I train machine learning models across multiple hospitals without sharing sensitive raw data?▼

Federated learning enables training models across multiple hospitals without sharing sensitive raw data by coordinating local model updates and aggregating them centrally. This Skill orchestrates that cross-site workflow while preserving privacy.

Can I apply differential privacy with DP-SGD to a Flower-based federated learning pipeline?▼

Yes, you can apply differential privacy via DP-SGD to a Flower-based federated learning pipeline. This Skill integrates DP-SGD to clip gradients and add noise during local training, ensuring mathematical privacy guarantees.

How do I handle non-IID data distributions when coordinating federated learning across different research institutions?▼

Handling non-IID data distributions in federated learning requires specific aggregation strategies. This Skill supports FedProx and FedOpt alongside FedAvg to effectively manage heterogeneous, non-IID data splits across different research institutions.

What is the best way to orchestrate cross-site federated learning workflows for scientific data analysis?▼

The best way to orchestrate cross-site federated learning for scientific data is using a framework like Flower. This Skill provides efficient cross-site coordination and workflow orchestration to manage distributed ML pipelines.

Does federated learning work for enterprises needing distributed ML with strict privacy requirements?▼

Federated learning works for enterprises needing distributed ML with strict privacy requirements by training models locally and sharing only updates. This Skill adds differential privacy to ensure raw enterprise data is never exposed.