alibaba/FederatedScope

Health v2 · maintenance only

Adoption not part of the score

1540 stars · 261 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FederatedScope is a comprehensive federated learning platform built on PyTorch with an event-driven architecture. It provides convenient usage and flexible customization for various federated learning tasks in both academia and industry.

Use cases

• run federated learning experiments across simulated clients
• benchmark federated learning algorithms
• research privacy-preserving machine learning
• simulate federated backdoor attacks and defenses
• tune hyperparameters for federated training
• train models on decentralized data without sharing raw data

When to choose

• you need a flexible, customizable federated learning framework for research
• you want an event-driven architecture that is easy to extend with new FL algorithms
• you need benchmarks for FL tasks like HPO or backdoor attacks

When to avoid

• you need production-grade cross-device federated learning on real edge devices
• you want a simple off-the-shelf FL solution without customization
• your project does not use PyTorch

Facets

framework · maturity active

machine-learning simulation benchmarking machine-learning artificial-intelligence privacy developer-tools python cross-platform federated-learning pytorch event-driven-architecture privacy-preserving research

Member repositories

For agents

markdown · JSON · MCP: product_card(name="alibaba/FederatedScope")