방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 강건한 연합 학습× | 온라인 연합 학습× | |
|---|---|---|
| 분야 | 머신러닝 | 머신러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2017 | 2019–2021 |
| 창시자≠ | Blanchard, P.; El Mhamdi, E. M.; Guerraoui, R. | McMahan, B. et al. (FL foundation); extended to online setting by multiple researchers c. 2019–2021 |
| 유형≠ | Distributed learning with Byzantine-tolerant aggregation | Distributed sequential learning |
| 원전≠ | Blanchard, P., El Mhamdi, E. M., Guerraoui, R., & Stainer, J. (2017). Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. Advances in Neural Information Processing Systems, 30. link ↗ | Damaskinos, G., Guerraoui, R., Kermarrec, A.-M., Guirguis, A., Riviere, M., & Tempo, R. (2020). FLEET: Flexible and Efficient Federated Learning for Edge AI. Proceedings of Machine Learning and Systems (MLSys). link ↗ |
| 별칭 | Byzantine-robust federated learning, fault-tolerant federated learning, robust FL, Byzantine-tolerant distributed learning | OFL, federated online learning, streaming federated learning, real-time federated learning |
| 관련≠ | 6 | 5 |
| 요약≠ | Robust Federated Learning extends standard federated learning with Byzantine-tolerant aggregation rules that protect the global model against malicious, corrupted, or unreliable clients. Instead of naively averaging client gradients, robust aggregation methods such as coordinate-wise median or Krum filter out harmful updates so that a minority of adversarial participants cannot derail training. | Online Federated Learning (OFL) combines the privacy-preserving, decentralised structure of federated learning with the sequential, sample-by-sample update regime of online learning. Clients — such as mobile devices or edge sensors — receive a global model, update it on newly arriving local data without sharing raw observations, and contribute compressed updates to a central server that aggregates them in near-real-time. |
| ScholarGate데이터셋 ↗ |
|
|