Table 4 Comparison of MSE and MAE prediction performance of different methods on Trento dataset.
From: Core network traffic prediction based on vertical federated learning and split learning
| Â | Trento | |||||
|---|---|---|---|---|---|---|
Methods | MSE | MAE | ||||
| Â | SMS | Call | Internet | SMS | Call | Internet |
SVR | 5.3142 | 1.1823 | 5.8086 | 1.1322 | 0.5721 | 1.0329 |
Lasso | 4.6123 | 1.6322 | 5.6235 | 1.3221 | 0.8342 | 1.5237 |
LSTM | 3.2384 | 1.2344 | 4.5723 | 0.9328 | 0.5217 | 1.1356 |
Fedavg | 2.1322 | 1.4563 | 4.5232 | 0.7525 | 0.5349 | 1.0348 |
VFL | \(\mathbf {1.8246}\) | \(\mathbf {1.0023}\) | \(\mathbf {2.3452}\) | \(\mathbf {0.6231}\) | \(\mathbf {0.4012}\) | \(\mathbf {0.7162}\) |
