Name
Title | ||
|---|---|---|
Challenging the generalization capabilities of Graph Neural Networks for network modeling. |
Abstract | ||
|---|---|---|
Today, network operators still lack functional network models able to make accurate predictions of end-to-end Key Performance Indicators (e.g., delay or jitter) at limited cost. Recently a novel Graph Neural Network (GNN) model called RouteNet was proposed as a cost-effective alternative to estimate the per-source/destination pair mean delay and jitter in networks. Thanks to its GNN architecture that operates over graph-structured data, RouteNet revealed an unprecedented ability to learn and model the complex relationships among topology, routing and input traffic in networks. As a result, it was able to make performance predictions with similar accuracy than resource-hungry packet-level simulators even in network scenarios unseen during training. In this demo, we will challenge the generalization capabilities of RouteNet with more complex scenarios, including larger topologies.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3342280.3342327 | SIGCOMM Posters and Demos |
Keywords | Field | DocType |
Graph Neural Networks, Network Modeling | Architecture,Performance indicator,Computer science,Graph neural networks,Network topology,Operator (computer programming),Jitter,Network model,Distributed computing | Conference |
ISBN | Citations | PageRank |
978-1-4503-6886-5 | 1 | 0.43 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| José Suárez-Varela | 1 | 9 | 4.33 |
| Sergi Carol-Bosch | 2 | 1 | 0.43 |
| Krzysztof Rusek | 3 | 41 | 7.20 |
| Paul Almasan | 4 | 3 | 2.21 |
| Marta Arias | 5 | 165 | 15.62 |
| Pere Barlet-ros | 6 | 269 | 27.74 |
| Albert Cabellos-Aparicio | 7 | 418 | 46.33 |