Towards more realistic network models based on Graph Neural Networks

Badia-Sampera, Arnau; Suárez-Varela, José; Almasan, Paul; Rusek, Krzysztof; Barlet‐Ros, Pere; Cabellos‐Aparicio, Albert

doi:10.1145/3360468.3366773

Cited by 16 publications

(15 citation statements)

References 6 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A limitation of the model is that it supports only topologies with identical link capacities. The model has been further explored by Suárez-Varela et al [91] and extended by Badia-Sampera et al [92] to model nodes (their queue size) too.…”

Section: ) Network Modelingmentioning

confidence: 99%

Learning Combinatorial Optimization on Graphs: A Survey With Applications to Networking

et al. 2020

View full text Add to dashboard Cite

Existing approaches to solving combinatorial optimization problems on graphs suffer from the need to engineer each problem algorithmically, with practical problems recurring in many instances. The practical side of theoretical computer science, such as computational complexity, then needs to be addressed. Relevant developments in machine learning research on graphs are surveyed for this purpose. We organize and compare the structures involved with learning to solve combinatorial optimization problems, with a special eye on the telecommunications domain and its continuous development of live and research networks.

show abstract

Section: ) Network Modelingmentioning

confidence: 99%

Learning Combinatorial Optimization on Graphs: A Survey With Applications to Networking

et al. 2020

View full text Add to dashboard Cite

show abstract

“…which extends the application of neural networks from Euclidean structure data to non-Euclidean structure data. GNN is based on the message passing mecha- IFIP Networking Conference (IFIP Networking) [63] International Conference on Information Networking (ICOIN) [64,65] International Conference on Information and Communication Technology Convergence (ICTC) [66] International Conference on Network and Service Management (CNSM) [67,68,69] International Conference on Real-Time Networks and Systems (RTNS) [70] International Conference on Wireless Communications and Signal Processing (WCSP) [71] International Conference on emerging Networking EXperiments and Technologies (CoNEXT) [72] International Symposium on Networks, Computers and Communications (IS-NCC) [73] Opto-Electronics and Communications Conference (OECC) [74] Table 4: List of source workshops and the corresponding studies we cover in this study.…”

Section: Journal Name Studiesmentioning

confidence: 99%

Graph-based Deep Learning for Communication Networks: A Survey

Jiang

2021

Preprint

View full text Add to dashboard Cite

Communication networks are important infrastructures in contemporary society. There are still many challenges that are not fully solved and new solutions are proposed continuously in this active research area. In recent years, to model the network topology, graph-based deep learning has achieved state-of-the-art performance in a series of problems in communication networks. In this survey, we review the rapidly growing body of research using different graph-based deep learning models, e.g. graph convolutional and graph attention networks, in various problems from different communication networks, e.g. wireless networks, wired networks, and software-defined networks. We also present a well-organized list of the problem and solution for each study and identify future research directions. To the best of our knowledge, this paper is the first survey that focuses on the application of graph-based deep learning methods in communication networks. To track the follow-up research, a public GitHub repository is created, where the relevant papers will be updated continuously.

show abstract

“…The strong generalization capabilities of GNN over graphs make these models interesting for applications in the networking ield since the most natural way to formalize many network control and management problems involves the use of graphs (e.g., topology, routing, interlow dependencies) [3]. Recently, several GNN-based solutions have been proposed to tackle different use cases in the ield of computer networks (e.g., network modeling [12,16], automatic routing protocols [13]). In this section, for illustrative purposes, we focus only on RouteNet [12], as it is quite representative of how GNNbased solutions represent and process network-related data to solve complex problems.…”

Section: Graph Neural Network Applied To Networkingmentioning

confidence: 99%

“…Note that when applying GNN to network-related problems, input graphs 𝐺 may contain a wide variety of elements and connections that do not necessarily correspond to physical network elements (e.g., forwarding devices, links). For instance, some proposals like [12,16] introduce complex hypergraphs including logic network entities (e.g., end-to-end paths).…”

Section: Explainability Maskmentioning

confidence: 99%

NetXplain: Real-time explainability of graph neural networks applied to networking

Pujol-Perich¹,

Surez-Varela²,

Xiao³

et al. 2021

ITU-J FET

View full text Add to dashboard Cite

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.

show abstract

Towards more realistic network models based on Graph Neural Networks

Cited by 16 publications

References 6 publications

Learning Combinatorial Optimization on Graphs: A Survey With Applications to Networking

Learning Combinatorial Optimization on Graphs: A Survey With Applications to Networking

Graph-based Deep Learning for Communication Networks: A Survey

NetXplain: Real-time explainability of graph neural networks applied to networking

Contact Info

Product

Resources

About