Federated Learning
Machine learning across distributed devices or organizations while keeping raw data local for privacy, latency, or governance reasons.
Core metadata
- ID: federated_learning
- Era: Modern
- First known date: 2016 (year)
- Region: Google / mobile-device machine learning
- Review status: source_checked
- Maturity: N/A
Prerequisites
- Edge Computing (edge_computing)
- Machine Learning (Early Algorithms) (machine_learning_early_algorithms)
- Zero Trust Security (zero_trust_security)
Dependents
Fields
- None.
Node sources
- Communication-Efficient Learning of Deep Networks from Decentralized Data (arXiv, 2016, primary_paper) • Supports: node
Prerequisite edge evidence
Edge/source evidence summary:
- Prerequisite edges: 3
- Average edge confidence: 70%
- Prerequisite sources: 2
- expert_inference: 3
| Prerequisite | Type | Confidence | Evidence level | Note | Sources |
|---|---|---|---|---|---|
| Machine Learning (Early Algorithms) (machine_learning_early_algorithms) | historical_predecessor | 75% | expert_inference | Machine Learning (Early Algorithms) is an earlier historical predecessor or foundation, not a one-to-one engineering dependency. |
|
| Edge Computing (edge_computing) | enabling | 68% | expert_inference | Edge Computing provides a capability that enables this technology without being the only possible path. | No sources recorded. |
| Zero Trust Security (zero_trust_security) | enabling | 68% | expert_inference | Zero Trust Security provides a capability that enables this technology without being the only possible path. |
|
This page is generated from canonical era JSON and is indexable by URL.