Graph Neural Networks for Wireless Communications: From Theory to Practice
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Deep learning-based approaches have been developed to solve challenging problems in wireless communications, leading to promising results. Early attempts adopted neural network architectures inherited from applications such as computer vision. They often yield poor performance in large scale networks (i.e., poor scalability) and unseen network settings (i.e., poor generalization). To resolve these issues, graph neural networks (GNNs) have been recently adopted, as they can effectively exploit the domain knowledge, i.e., the graph topology in wireless communications problems. GNN-based methods can achieve near-optimal performance in large-scale networks and generalize well under different system settings, but the theoretical underpinnings and design guidelines remain elusive, which may hinder their practical implementations. This paper endeavors to fill both the theoretical and practical gaps. For theoretical guarantees, we prove that GNNs achieve near-optimal performance in wireless networks with much fewer training samples than traditional neural architectures. Specifically, to solve an optimization problem on an$n$-node graph (where the nodes may represent users, base stations, or antennas), GNNs’ generalization error and required number of training samples are$\mathcal {O}(n)$and$\mathcal {O}(n^{2})$times lower than the unstructured multi-layer perceptrons. For design guidelines, we propose a unified framework that is applicable to general design problems in wireless networks, which includes graph modeling, neural architecture design, and theory-guided performance enhancement. Extensive simulations, which cover a variety of important problems and network settings, verify our theory and the effectiveness of the proposed design framework.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279 · cited 4×
“3) GNNs Versus Model-Driven Deep Learning: GNNs can be used in a data-driven manner [3], [13], [20] or integrated with model-driven methods [12], [15], [17].”
BackgroundMethodInfluentialShi, 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×
“Proposition 2: [WMMSE as a DMP Algorithm] The weighted minimum mean square error (WMMSE) algorithm (Algorithm 1 in [2]) for solving Problem (3) is a DMP algorithm.”
BackgroundInfluentialEdge 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 · cited 10×
“For statistical inference problems, GNNs are robust to the change of SNR level, number of antennas, and the number of users [14].”
InfluentialSelf-citationShen, Y., Shi, Y., Zhang, J., & Letaief, K. B. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036965 · Cited by 367
Self-citationOptimal 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 8×
“Second, the qualitative results of [3], [12], [16], [20] cannot be used to guide a better design of GNN-based algorithms, i.”
BackgroundMethodInfluentialHu, Q., Cai, Y., Shi, Q., Xu, K., Yu, G., & Ding, Z. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3033334 · Cited by 253
Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
Sohrabi, F., Attiah, K. M., & Yu, W. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3055202 · Cited by 169
Unfolding WMMSE Using Graph Neural Networks for Efficient Power Allocation
Chowdhury, A., Verma, G., Rao, C., Swami, A., & Segarra, S. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3071480 · Cited by 162
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 3×
“Such advantage is a major motivation underlying the recent interests in “learning to optimize” approaches [2], [3], [8].”
BackgroundResultSelf-citationNeural Calibration for Scalable Beamforming in FDD Massive MIMO with Implicit Channel Estimation
Ma, Y., Shen, Y., Yu, X., Zhang, J., Song, S. H., & Letaief, K. B. (2021) · 2021 IEEE Global Communications Conference (GLOBECOM) · doi:10.1109/globecom46510.2021.9685574 · Cited by 15
Self-citation
Metadata
- Authors
- Shen, Y., Zhang, J., Song, S. H., & Letaief, K. B.
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2023-05
- Volume
- 22
- Issue
- 5
- Pages
- 3554-3569
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W4221150253
- Cited by
- 230
- References
- 11
- FWCI
- 13.73
- Type
- journal article
- Language
- en
- Open access
- green
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.