Federated Learning
Cross-source consensus on Federated Learning from 1 sources and 5 claims.
1 sources · 5 claims
How it works
Benefits
Risks & contraindications
Highlighted claims
- Federated learning trains models across decentralized datasets without moving raw data from source institutions. — Global approaches to infectious disease surveillance and modeling
- Federated learning is valuable for infectious disease surveillance because patient data may be restricted across jurisdictions. — Global approaches to infectious disease surveillance and modeling
- Heterogeneous non-IID data are a central technical challenge for federated learning. — Global approaches to infectious disease surveillance and modeling
- Federated learning is vulnerable to bias propagation and adversarial privacy or security attacks. — Global approaches to infectious disease surveillance and modeling
- Covariate shift across federated sites can be mitigated through weighting approaches. — Global approaches to infectious disease surveillance and modeling