Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities

Suárez-Varela, José; Almasan, Paul; Ferriol-Galmés, Miquel; Rusek, K.; Geyer, Fabien; Cheng, Xiangle; Xiang, Sheng; Xiao, Shihan; Scarselli, Franco; Cabellos‐Aparicio, Albert; Barlet‐Ros, Pere

doi:10.1109/mnet.123.2100773

Cited by 32 publications

(20 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The graph-structured topology of wireless network enables the successful usage of GNN to solve a broad range of design problems over the wireless networks [80]. As a specialized NN for graph-structured data, GNN can exploit the domain knowledge of various applications to achieve near-optimal learning performance with good scalability and generalizability.…”

Section: Graph Neural Network For Structured Optimizationmentioning

confidence: 99%

“…First, the permutation invariance and permutation equivariance properties of GNNs enable the learned NN to adapt to large-scale and dynamic scenarios by exploiting the analogies or equivalent patterns between the training network topology and dynamic testing conditions automatically. Second, GNNs leverage the distributed message passing architecture to learn local relationships among graph nodes and combinatorial generalization over graphs [80]. As a result, GNNs can generalize to large-scale communication networks with varying sizes and permuted structures (e.g., more users, antennas, BSs, etc.…”

Section: G Advantages and Disadvantagesmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Large-Scale Optimization in 6G Wireless Networks

Shi¹,

Lian²,

Shi³

et al. 2023

Preprint

View full text Add to dashboard Cite

The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from "connected things" to "connected intelligence", featured by ultra high density, largescale, dynamic heterogeneity, diversified functional requirements and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms. The classic optimization-based algorithms usually require highly precise mathematical model of data links and suffer from poor performance with high computational cost in realistic 6G applications. Based on domain knowledge (e.g., optimization models and theoretical tools), machine learning (ML) stands out as a promising and viable methodology for many complex large-scale optimization problems in 6G, due to its superior performance, generalizability, computational efficiency and robustness. In this paper, we systematically review the most representative "learning to optimize" techniques in diverse domains of 6G wireless networks by identifying the inherent feature of the underlying optimization problem and investigating the specifically designed ML frameworks from the perspective of optimization. In particular, we will cover algorithm unrolling, learning to branch-andbound, graph neural network for structured optimization, deep reinforcement learning for stochastic optimization, as well as endto-end learning for semantic optimization, for solving challenging large-scale optimization problems arising from various important wireless applications. To enable ML implementation in distributed wireless networks across massive number of end devices, federated learning for distributed optimization will further be presented. Through the in-depth discussion, we shed light on the excellent performance of ML-based optimization algorithms with respect to the classical methods, and provide insightful guidance to develop advanced ML techniques in 6G networks. Neural network design, theoretical tools of different ML methods,

show abstract

Section: Graph Neural Network For Structured Optimizationmentioning

confidence: 99%

Section: G Advantages and Disadvantagesmentioning

confidence: 99%

Machine Learning for Large-Scale Optimization in 6G Wireless Networks

Shi¹,

Lian²,

Shi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In line with previous research [33], such generalisation was not observed in terms of topology: Te agent trained in the NFSNet topology did not perform well in the COST 239 topology and vice versa. Studying the beneft of using Graph Neural Networks to overcome the lack of topology generalisation is part of current research [63].…”

Section: Trpo Agent Vs Heuristic: Blocking Performancementioning

confidence: 99%

Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach

et al. 2023

View full text Add to dashboard Cite

A deep reinforcement learning (DRL) approach is applied, for the first time, to solve the routing, modulation, spectrum, and core allocation (RMSCA) problem in dynamic multicore fiber elastic optical networks (MCF-EONs). To do so, a new environment was designed and implemented to emulate the operation of MCF-EONs - taking into account the modulation format-dependent reach and intercore crosstalk (XT) - and four DRL agents were trained to solve the RMSCA problem. The blocking performance of the trained agents was compared through simulation to 3 baselines RMSCA heuristics. Results obtained for the NSFNet and COST239 network topologies under different traffic loads show that the best-performing agent achieves, on average, up to a four-times decrease in blocking probability with respect to the best-performing baseline heuristic method.

show abstract

“…GNNs are a subclass of DL models specifically designed to work on graph-structured data [2], and have been successfully applied to many different fields, including chemistry, biology, or computer vision [23]. In the field of communication networks, GNNs have been applied to a variety of tasks [17], such as routing optimization [15], power control in wireless networks [16], Distributed Denial of Service (DDoS) attack detection [12], or network intrusion detection [13].…”

Section: Related Workmentioning

confidence: 99%

Detecting Contextual Network Anomalies with Graph Neural Networks

Latif,

Suárez-Varela,

Cabellos-Aparicio

et al. 2023

Proceedings of the 2nd on Graph Neural Networking Workshop 2023

Self Cite

View full text Add to dashboard Cite

Detecting anomalies on network traffic is a complex task due to the massive amount of traffic flows in today's networks, as well as the highly-dynamic nature of traffic over time. In this paper, we propose the use of Graph Neural Networks (GNN) for network traffic anomaly detection. We formulate the problem as contextual anomaly detection on network traffic measurements, and propose a custom GNN-based solution that detects traffic anomalies on origin-destination flows. In our evaluation, we use real-world data from Abilene (6 months), and make a comparison with other widely used methods for the same task (PCA, EWMA, RNN). The results show that the anomalies detected by our solution are quite complementary to those captured by the baselines (with a max. of 36.33% overlapping anomalies for PCA). Moreover, we manually inspect the anomalies detected by our method, and find that a large portion of them can be visually validated by a network expert (64% with high confidence, 18% with mid confidence, 18% normal traffic). Lastly, we analyze the characteristics of the anomalies through two paradigmatic cases that are quite representative of the bulk of anomalies.

show abstract

Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities

Cited by 32 publications

References 14 publications

Machine Learning for Large-Scale Optimization in 6G Wireless Networks

Machine Learning for Large-Scale Optimization in 6G Wireless Networks

Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach

Detecting Contextual Network Anomalies with Graph Neural Networks

Contact Info

Product

Resources

About