Oracle-based data generation for highly efficient digital twin network training
ITU Journal on Future and Evolving Technologies · 2023
DOI: 10.52953/aweu6345 ↗Kurz gefasst
Fachartikel in der Zeitschrift ITU Journal on Future and Evolving Technologies, 2023. Verfasst von Eliyahu Sason und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent advances in Graph Neural Networks (GNNs) has opened new capabilities to analyze complex communication systems. However, little work has been done to study the effects of limited data samples on the performance of GNN-based systems. In this paper, we present a novel solution to the problem of finding an optimal training set for efficient training of a RouteNet-Fermi GNN model. The proposed solution ensures good model generalization to large previously unseen networks under strict limitations on the training data budget and training topology sizes. Specifically, we generate an initial data set by emulating the flow distribution of large networks while using small networks. We then deploy a new clustering method that efficiently samples the above generated data set by analyzing the data embeddings from different Oracle models. This procedure provides a very small but information-rich training set. The above data embedding method translates highly heterogeneous network samples into a common embedding spac, wherein the samples can be easily related to each other. The proposed method outperforms state-of-the-art approaches, including the winning solutions of the 2022 Graph Neural Networking challenge.
Zitieren
APA
Sason, E., Lubarsky, Y., Gaissinski, A., Kravchik, E., & Kisilev, P. (2023). Oracle-based data generation for highly efficient digital twin network training. ITU Journal on Future and Evolving Technologies. https://doi.org/10.52953/aweu6345
Vancouver
Sason E, Lubarsky Y, Gaissinski A, Kravchik E, Kisilev P. Oracle-based data generation for highly efficient digital twin network training. ITU Journal on Future and Evolving Technologies. 2023. doi:10.52953/aweu6345
BibTeX
@article{Sason2023,
author = {Sason, Eliyahu and Lubarsky, Yackov and Gaissinski, Alexei and Kravchik, Eli and Kisilev, Pavel},
title = {Oracle-based data generation for highly efficient digital twin network training},
journal = {ITU Journal on Future and Evolving Technologies},
year = {2023},
doi = {10.52953/aweu6345}
}
EUVIMED