What is federated learning?
hardAnswer
- Train model across decentralized devices holding local data — data never leaves device.
- Rounds: (1) server sends global model.
- (2) each device trains locally on private data.
- (3) devices send gradients / weight deltas to server.
- (4) server aggregates (FedAvg).
- Advantages: privacy + reduced bandwidth.
- Challenges: non-IID data, straggling devices, gradient inversion attacks (defend with secure aggregation + DP).
- Google Gboard next-word prediction is canonical example.
Check yourself — multiple choice
- Random
- Train across decentralized devices, data never leaves; rounds: server → local train → aggregate (FedAvg); privacy + bandwidth win; non-IID + straggler + inversion challenges
- Same as distributed
- Not real
Federated learning: local train + aggregate on server (FedAvg).
#safety#advanced
Practise MLOps & Data Quality
215 interview questions in this topic.