Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
Deep learning has recently emerged as a disruptive technology to solve challenging radio resource management problems in wireless networks. However, the neural network architectures adopted by existing works suffer from poor scalability and generalization, and lack of interpretability. A long-standing approach to improve scalability and generalization is to incorporate the structures of the target task into the neural network architecture. In this paper, we propose to apply graph neural networks (GNNs) to solve large-scale radio resource management problems, supported by effective neural network architecture design and theoretical analysis. Specifically, we first demonstrate that radio resource management problems can be formulated as graph optimization problems that enjoy a universal permutation equivariance property. We then identify a family of neural networks, namedmessage passing graph neural networks(MPGNNs). It is demonstrated that they not only satisfy the permutation equivariance property, but also can generalize to large-scale problems, while enjoying a high computational efficiency. For interpretablity and theoretical guarantees, we prove the equivalence between MPGNNs and a family of distributed optimization algorithms, which is then used to analyze the performance and generalization of MPGNN-based methods. Extensive simulations, with power control and beamforming as two examples, demonstrate that the proposed method, trained in an unsupervised manner with unlabel…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For instances, distributed RL [55], decentralized graph neural networks [23], and distributed DNN [61], are able to automatically learn the distributed resource allocation optimization algorithms.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [23]
In the citing paper
“For scalable radio resource allocation application via DL, the inference latency must be within the channel coherence time (e.g., 10ms) to yield a meaningful resource allocation decision [23].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [23]
In the citing paper
“Graph neural network (GNN) has recently been shown to be able to harness the benefits of generalizability, interpretability, robustness, scalability, superior performance, real-time and distributed implementation for learning to optimize nonconvex problems, including power control [270], beamforming [23], and phase shift design [25].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [23]
In the citing paper
“In particular, edge AI techniques, including distributed RL [55], [301], decentralized GNN [23], as well as distributed DNN with binarized output layer [61], are able to learn and execute the distributed resource allocation polices in an automatic and real-time manner.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [23]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“This motivates researchers to develop GNNs [29], which effectively exploit the graph structure.”
BackgroundPointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles, R. Q., Su, H., Kaichun, M., & Guibas, L. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.16 · Cited by 9,237
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
Dynamic Graph CNN for Learning on Point Clouds
Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019) · ACM Transactions on Graphics · doi:10.1145/3326362 · Cited by 7,199
Formal Semantics for Kolmogorov-Arnold Network Representations of Operational Games
Zhukov, G. A. (2025) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.15206559 · Cited by 3,212
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. (2020) · UTS ePRESS (University of Technology Sydney) · Cited by 3,174
Shi, Q., Razaviyayn, M., Luo, Z.-Q., & He, C. (2011) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2011.2147784 · Cited by 2,129 · cited 7×
“Here, we consider WMMSE [18] in the original paper’s setting, which includes (5) as a special case.”
BackgroundMethodInfluentialFast Graph Representation Learning with PyTorch Geometric
Fey, M., & Lenssen, J. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02428 · Cited by 1,132
Learning to Optimize: Training Deep Neural Networks for Interference Management
Sun, H., Chen, X., Shi, Q., Hong, M., Fu, X., & Sidiropoulos, N. D. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2866382 · Cited by 874
Shi, Q., Razaviyayn, M., Luo, Z.-Q., & He, C. (2011) · 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2011.5946304 · Cited by 873
Bjornson, E., Bengtsson, M., & Ottersten, B. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2312183 · Cited by 606
Group Sparse Beamforming for Green Cloud-RAN
(2014) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2014.040214.131770 · Cited by 468 · cited 3×
“the optimization-based methods in [19], [20].”
MethodSelf-citationDiscriminative Embeddings of Latent Variable Models for Structured Data
Dai, H., Dai, B., & Song, L. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.05629 · Cited by 454
Differentiable Convex Optimization LayersPreprint
Agrawal, A., Amos, B., Barratt, S. T., Boyd, S., Diamond, S., & Kolter, J. Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12430 · Cited by 395
Power Control in Wireless Cellular Networks
Chiang, M., Hande, P., Lan, T., & Tan, C. W. (2007) · now publishers, Inc. eBooks · doi:10.1561/9781601981370 · Cited by 361
A Deep Learning Framework for Optimization of MISO Downlink Beamforming
Xia, W., Zheng, G., Zhu, Y., Zhang, J., Wang, J., & Petropulu, A. P. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2960361 · Cited by 345 · cited 1×
“Most of the existing works adopt MLPs [7], [9], [11], [21] or convolutional neural networks (CNNs) [8], [12].”
BackgroundSelf-citationHow Powerful are Graph Neural Networks?
Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00826 · Cited by 332
THE LOGICAL EXPRESSIVENESS OF GRAPH NEURAL NETWORKS
Barceló, P., Kostylev, E. V., Monet, M., Pérez, J. E. P., Reutter, J. L., & Silva, J.-P. (2020) · HAL · Cited by 329
Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks
Eisen, M., & Ribeiro, A. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2988255 · Cited by 327 · cited 6×
“cannot be solved by existing methods in [10], [13], [14].”
BackgroundMethodInfluentialApproximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
Brendel, W., & Bethge, M. (2019) · arXiv · doi:10.48550/arxiv.1904.00760 · Cited by 323
Distributed algorithms for transmission power control in wireless sensor networks
Kubisch, M., Karl, H., Wolisz, A., Zhong, L. C., & Rabaey, J. (2004) · 2003 IEEE Wireless Communications and Networking, 2003. WCNC 2003. · doi:10.1109/wcnc.2003.1200410 · Cited by 321
Deep Power Control: Transmit Power Control Scheme Based on Convolutional Neural Network
Lee, W., Kim, M., & Cho, D.-H. (2018) · IEEE Communications Letters · doi:10.1109/lcomm.2018.2825444 · Cited by 305
Power Control in Wireless Cellular Networks
Chiang, M., Hande, P., Lan, T., & Tan, C. W. (2008) · Foundations and Trends in Networking · doi:10.1561/1300000009 · Cited by 304
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
Li, Z., Chen, Q., & Koltun, V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10659 · Cited by 287
Deep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks
Liang, L., Ye, H., Yu, G., & Li, G. Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2957798 · Cited by 282
Zaheer, M., Kottur, S., Ravanbakhsh, S., Póczos, B., Salakhutdinov, R. R., & Smola, A. J. (2017) · neural information processing systems · Cited by 279
Towards Optimal Power Control via Ensembling Deep Neural Networks
Liang, F., Shen, C., Yu, W., & Wu, F. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2957482 · Cited by 268
Spatial Deep Learning for Wireless Scheduling
Cui, W., Shen, K., & Yu, W. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2904352 · Cited by 265
Equivariance Through Parameter-SharingPreprint
Ravanbakhsh, S., Schneider, J., & Póczos, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.08389 · Cited by 244
Machine learning for combinatorial optimization: A methodological tour d'horizon
Bengio, Y., Lodi, A., & Prouvost, A. (2021) · European Journal of Operational Research · doi:10.1016/j.ejor.2020.07.063 · Cited by 195
Graph Embedding-Based Wireless Link Scheduling With Few Training Samples
Lee, M., Yu, G., & Li, G. Y. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3040983 · Cited by 180
Approximation Ratios of Graph Neural Networks for Combinatorial ProblemsPreprint
Sato, R., Yamada, M., & Kashima, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10261 · Cited by 144
LORM: Learning to Optimize for Resource Management in Wireless Networks With Few Training Samples
Shen, Y., Shi, Y., Zhang, J., & Letaief, K. B. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2947591 · Cited by 134 · cited 4×
“Most of existing works on “learning to optimize” approaches to solve problems in wireless networks adopted MLPs as the neural network architecture [7], [9], [11].”
BackgroundMethodInfluentialSelf-citationLarge-Scale Convex Optimization for Dense Wireless Cooperative Networks
Shi, Y., Zhang, J., O'Donoghue, B., & Letaief, K. B. (2015) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2015.2443731 · Cited by 118
Self-citationLarge-scale convex optimization for ultra-dense cloud-RAN
Shi, Y., Zhang, J., Letaief, K. B., Bai, B., & Chen, W. (2015) · IEEE Wireless Communications · doi:10.1109/mwc.2015.7143330 · Cited by 108
Self-citationWhat Can Neural Networks Reason About?
Xu, K., Li, J., Zhang, M., Du, S. S., Kawarabayashi, K., & Jegelka, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13211 · Cited by 90
A Graph Neural Network Approach for Scalable Wireless Power Control
Shen, Y., Shi, Y., Zhang, J., & Letaief, K. B. (2019) · 2019 IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps45667.2019.9024538 · Cited by 87
Self-citationRE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection
Pratik, K., Rao, B. D., & Welling, M. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3045199 · Cited by 75
Weak models of distributed computing, with connections to modal logic
Hella, L., Järvisalo, M., Kuusisto, A., Laurinharju, J., Lempiäinen, T., Luosto, K., Suomela, J., & Virtema, J. (2013) · Distributed Computing · doi:10.1007/s00446-013-0202-3 · Cited by 73
FPLinQ: A cooperative spectrum sharing strategy for device-to-device communications
Shen, K., & Yu, W. (2017) · 2017 IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2017.8006944 · Cited by 72
Toward Greater Intelligence in Route Planning: A Graph-Aware Deep Learning Approach
Zhuang, Z., Wang, J., Qi, Q., Sun, H., & Liao, J. (2019) · IEEE Systems Journal · doi:10.1109/jsyst.2019.2922217 · Cited by 30
Faster Activity and Data Detection in Massive Random Access: A Multiarmed Bandit Approach
Dong, J., Zhang, J., Shi, Y., & Wang, J. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3142185 · Cited by 28
Self-citationEnhanced Group Sparse Beamforming for Green Cloud-RAN: A Random Matrix Approach
Shi, Y., Zhang, J., Chen, W., & Letaief, K. B. (2018) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2018.2797203 · Cited by 24
Self-citationData Representation for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks.Preprint
Sun, C., Wu, J., & Yang, C. (2020) · arXiv (Cornell University) · Cited by 1
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Research works printed but not linked: 2
- zaheer, 2017, Deep sets, Proc Adv Neural Inf Process Syst, 3391
- goodfellow, 2016, Deep Learning
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
Self-citationXu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3239189 · Cited by 660
Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
Shao, J., Mao, Y., & Zhang, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126087 · Cited by 338
Self-citationZhou, X., Liang, W., Li, W., Yan, K., Shimizu, S., & Wang, K. I.-K. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3130434 · Cited by 325
Jiang, T., Cheng, H. V., & Yu, W. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3078502 · Cited by 290
Metadata
- Authors
- Shen, Y., Shi, Y., Zhang, J., & Letaief, K. B.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- ShanghaiTech University (CN)
- Hong Kong Polytechnic University (HK)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-01
- Volume
- 39
- Issue
- 1
- Pages
- 101-115
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3111499798
- Cited by
- 367
- References
- 48
- Citations by year
- 2026: 48 · 2025: 90 · 2024: 90 · 2023: 72 · 2022: 39 · 2021: 26
- FWCI
- 11.92
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- General Research Fund from the Research Grants Council of Hong Kong (16210719)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced MIMO Systems Optimization
- Keywords
- graph neural networks, radio resource management, message-passing graph neural networks, permutation equivariance, graph optimization, distributed optimization algorithms, power control, beamforming, interference channel, scalability, generalization, interpretability, unsupervised learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.