Federated Learning Architect
Designs privacy-preserving distributed machine learning systems using federated learning. Covers federated averaging, differential privacy, secure aggregation, communication efficiency, and compliance with privacy regulations.
SupaScore
84.8Best for
- ▸Design cross-device federated learning for mobile apps with 10M+ users under GDPR
- ▸Architect cross-silo federated training for healthcare consortiums handling HIPAA data
- ▸Implement differential privacy mechanisms for financial federated learning (ε < 1)
- ▸Build secure aggregation protocols for industrial IoT federated training
- ▸Design federated learning systems for multi-bank fraud detection with regulatory compliance
What you'll get
- ●Comprehensive federated architecture diagram with FedAvg configuration, differential privacy parameters (ε=0.5, δ=1e-5), secure aggregation protocol, and GDPR compliance mapping
- ●Technical implementation guide with client selection strategy, communication rounds optimization, non-IID mitigation using FedProx, and privacy audit procedures
- ●Production deployment plan with failure modes, privacy budget allocation across training rounds, and regulatory documentation requirements
Not designed for ↓
- ×Traditional centralized machine learning or standard distributed training
- ×Basic differential privacy implementation without federated learning context
- ×General privacy consulting without technical federated system design
- ×Blockchain-based decentralized learning or cryptocurrency applications
Clear privacy requirements (regulatory context, threat model, privacy budget), data distribution characteristics (cross-device vs cross-silo, IID vs non-IID), and technical constraints (communication bandwidth, client reliability, compute capacity).
Detailed federated learning architecture with privacy mechanisms, aggregation algorithms, communication protocols, compliance mappings, and implementation recommendations with specific parameter configurations.
Evidence Policy
Enabled: this skill cites sources and distinguishes evidence from opinion.
Research Foundation: 7 sources (3 paper, 1 books, 3 official docs)
This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.
Version History
Initial release
Prerequisites
Use these skills first for best results.
Works well with
Need more depth?
Specialist skills that go deeper in areas this skill touches.
Common Workflows
Privacy-First ML System Design
End-to-end privacy-preserving ML system from federated architecture through compliance validation to production deployment
Activate this skill in Claude Code
Sign up for free to access the full system prompt via REST API or MCP.
Start Free to Activate This Skill© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice