NetXplain: Real-time explainability of graph neural networks applied to networking
ITU Journal on Future and Evolving Technologies · 2021
DOI: 10.52953/akzh5253 ↗Kurz gefasst
Fachartikel in der Zeitschrift ITU Journal on Future and Evolving Technologies, 2021. Verfasst von David Pujol-Perich und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent advancements in Deep Learning (DL) have revolutionized the way we can efficiently tackle complex optimization problems. However, existing DL-based solutions are often considered as black boxes with high inner complexity. As a result, there is still certain skepticism among the networking industry about their practical viability to operate data networks. In this context, explainability techniques have recently emerged to unveil why DL models make each decision. This paper focuses on the explainability of Graph Neural Networks (GNNs) applied to networking. GNNs are a novel DL family with unique properties to generalize over graphs. As a result, they have shown unprecedented performance to solve complex network optimization problems. This paper presents NetXplain, a novel real-time explainability solution that uses a GNN to interpret the output produced by another GNN. In the evaluation, we apply the proposed explainability method to RouteNet, a GNN model that predicts end-to-end QoS metrics in networks. We show that NetXplain operates more than 3 orders of magnitude faster than state-of-the-art explainability solutions when applied to networks up to 24 nodes, which makes it compatible with real-time applications; while demonstrating strong capabilities to generalize to network scenarios not seen during training.
Zitieren
APA
Pujol-Perich, D., Su�rez-Varela, J., Xiao, S., Wu, B., Cabellos-Aparicio, A., & Barlet-Ros, P. (2021). NetXplain: Real-time explainability of graph neural networks applied to networking. ITU Journal on Future and Evolving Technologies. https://doi.org/10.52953/akzh5253
Vancouver
Pujol-Perich D, Su�rez-Varela J, Xiao S, Wu B, Cabellos-Aparicio A, Barlet-Ros P. NetXplain: Real-time explainability of graph neural networks applied to networking. ITU Journal on Future and Evolving Technologies. 2021. doi:10.52953/akzh5253
BibTeX
@article{PujolPerich2021,
author = {Pujol-Perich, David and Su�rez-Varela, Jos� and Xiao, Shihan and Wu, Bo and Cabellos-Aparicio, Albert and Barlet-Ros, Pere},
title = {NetXplain: Real-time explainability of graph neural networks applied to networking},
journal = {ITU Journal on Future and Evolving Technologies},
year = {2021},
doi = {10.52953/akzh5253}
}
EUVIMED