So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Học Liên kết Mạnh mẽ× | Khuếch đại Gradient Mạnh mẽ× | |
|---|---|---|
| Lĩnh vực | Học máy | Học máy |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2017 | 2001 |
| Người khởi xướng≠ | Blanchard, P.; El Mhamdi, E. M.; Guerraoui, R. | Friedman, J. H. (with Huber loss from Huber, P. J.) |
| Loại≠ | Distributed learning with Byzantine-tolerant aggregation | Ensemble (boosted trees with robust loss) |
| Công trình gốc≠ | 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 ↗ | Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. DOI ↗ |
| Tên gọi khác | Byzantine-robust federated learning, fault-tolerant federated learning, robust FL, Byzantine-tolerant distributed learning | gradient boosting with Huber loss, robust GBM, outlier-robust boosting, robust gradient-boosted trees |
| Liên quan | 6 | 6 |
| Tóm tắt≠ | 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. | Robust Gradient Boosting is gradient boosting trained with outlier-resistant loss functions — most commonly the Huber loss or quantile (pinball) loss — instead of squared-error loss. Proposed in Friedman's seminal 2001 paper, this variant produces predictions far less distorted by extreme values or contaminated labels, while retaining the full predictive power of gradient-boosted trees. |
| ScholarGateBộ dữ liệu ↗ |
|
|