Szczegóły publikacji
Opis bibliograficzny
Challenging the generalization capabilities of Graph Neural Networks for network modeling / José Suárez-Varela, Sergi Carol-Bosch, Krzysztof RUSEK, Paul Almasan, Marta Arias, Pere Barlet-Ros, Albert Cabellos-Aparicio // W: SIGCOMM posters and demos '19 [Dokument elektroniczny] : proceedings of the ACM SIGCOMM 2019 conference posters and demos : Beijing, China, 19–24 August 2019. — Wersja do Windows. — Dane tekstowe. — New York : ACM, cop. 2019. — e-ISBN: 978-1-4503-6886-5. — S. 114–115. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://dl.acm.org/doi/pdf/10.1145/3342280.3342327?download=true [2020-02-27]. — Bibliogr. s. 115, Abstr. — K. Rusek - pierwsza afiliacja: Universitat Politècnica de Catalunya, Barcelona, Spain
Autorzy (7)
- Suárez-Varela José
- Carol-Bosch Sergi
- AGHRusek Krzysztof
- Almasan Paul
- Arias Marta
- Barlet-Ros Pere
- Cabellos-Aparicio Albert
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 123835 |
|---|---|
| Data dodania do BaDAP | 2020-02-27 |
| DOI | 10.1145/3342280.3342327 |
| Rok publikacji | 2019 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Association for Computing Machinery (ACM) |
| Konferencja | ACM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication 2019 |
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.
