Learning to Reflect and to Beamform for Intelligent Reflecting Surface With Implicit Channel Estimation
The DOI matches its Crossref record; 40 of the 42 references it cites were found in a registry or an index.
Abstract
Intelligent reflecting surface (IRS), which consists of a large number of tunable reflective elements, is capable of enhancing the wireless propagation environment in a cellular network by intelligently reflecting the electromagnetic waves from the base-station (BS) toward the users. The optimal tuning of the phase shifters at the IRS is, however, a challenging problem, because due to the passive nature of reflective elements, it is difficult to directly measure the channels between the IRS, the BS, and the users. Instead of following the traditional paradigm of first estimating the channels then optimizing the system parameters, this paper advocates a machine learning approach capable of directly optimizing both the beamformers at the BS and the reflective coefficients at the IRS based on a system objective. This is achieved by using a deep neural network to parameterize the mapping from the received pilots (plus any additional information, such as the user locations) to an optimized system configuration, and by adopting a permutation invariant/equivariant graph neural network (GNN) architecture to capture the interactions among the different users in the cellular network. Simulation results show that the proposed implicit channel estimation based approach is generalizable, can be interpreted, and can efficiently learn to maximize a sum-rate or minimum-rate objective from a much fewer number of pilots than the traditional explicit channel estimation based approaches.
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.
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
“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 [25]
In the citing paper
“For instance, the GNN was adopted to model the permutation invariant and equivalent properties of the mapping function for resource allocation in the RIS empowered TDD wireless networks [25].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [25]
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
How Powerful are Graph Neural Networks?
Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2018) · arXiv · doi:10.48550/arxiv.1810.00826 · Cited by 6,078
Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamforming
Wu, Q., & Zhang, R. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2936025 · Cited by 4,566
Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication
Huang, C., Zappone, A., Alexandropoulos, G. C., Debbah, M., & Yuen, C. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2922609 · Cited by 3,761
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
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 1×
“As a trivial baseline, we also show the performance of the system with random phase shifts, while the beamforming matrix W is optimized using the WMMSE algorithm [39] assuming perfect CSI, to see how much gain we can obtain by jointly optimizing the phase shifts and the beamforming matrix.”
MethodHolographic MIMO Surfaces for 6G Wireless Networks: Opportunities, Challenges, and Trends
Huang, C., Hu, S., Alexandropoulos, G. C., Zappone, A., Yuen, C., Zhang, R., Renzo, M. D., & Debbah, M. (2020) · IEEE Wireless Communications · doi:10.1109/mwc.001.1900534 · Cited by 1,342
Fast 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
Research works printed but not linked: 3
- [31] ¨ O. ¨ Ozdogan and E. Bj¨ ornson, 'Deep learning-based phase reconfiguration for intelligent reflecting surfaces,' in Proc. IEEE Asilomar Conf. Signals, Syst., Comput. , Nov. 2020. -
- [37] M. Abadi et al. , 'TensorFlow: Large-scale machine learning on heterogeneous systems,' 2015, software available from tensorflow.org. [Online]. Available: https://www.tensorflow.org/ -
- [36] E. Bj¨ ornson and L. Sanguinetti, 'Rayleigh fading modeling and channel hardening for reconfigurable intelligent surfaces,' IEEE Wireless Commun. Lett. , vol. 10, no. 4, pp. 830-834, April 2021. -
Cited by
Items 301–335 of 335
Optimization-Driven DRL in Wireless Networks
Gong, S., Niyato, D. T., Gu, B., & Huang, K. (2026) · Wireless networks · doi:10.1007/978-3-032-22997-7_2
Machine-Learning-Based Design of RIS-Enabled Wireless Systems
Liu, M., Huang, C., & Yuen, C. (2026) · Springer eBooks · doi:10.1007/978-981-95-1814-2_7
Novel CSI Acquisition and Energy-Aware Control for Beyond Diagonal RIS Architectures
Samy, M., Al-Hraishawi, H., Adam, A. B. M., Alsenwi, M., Chatzinotas, S., & Ottersten, B. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3741948
Scalable Pilot, Feedback and Precoding Design for Fdd Multi-User MIMO via Deep Learning
Zhu, L., Zhu, W., Zhang, S., Liu, L., & Cui, S. R. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161509
Das Lernen der Signalisierung von Kanalzustandsinformationen in der drahtlosen Kommunikation
Rizzello, V., Utschick, W., & München, T. U. (2024)
Multi-User Localization via Active Sensing with Electromagnetically Reconfigurable AntennasPreprint
Zhang, R., Zhang, Y., Zhang, Y., & Wymeersch, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.26605
Mendes, D., Souto, N. M. B., Pavia, J. P., & Silva, J. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3666997
Over-the-Air Interference Nulling Using Active RISPreprint
Wang, J., Sun, J., Liao, L., Liao, X., & Liu, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.22239
Zameni, S., Taheri, M., & Pouladi, H. (2026) · Ad Hoc Networks · doi:10.1016/j.adhoc.2026.104465
Max-Min Rate Optimization for Uplink IRS NOMA with Receive BeamformingPreprint
Cantos, L., Choi, J.-H., Awais, M., & Kim, Y. H. (2022) · doi:10.36227/techrxiv.20069852.v1
An Optimized Neural Network-based Channel Estimation Approach for Noma Using MimoPreprint
Dev, J., & Judson, D. (2023) · Research Square · doi:10.21203/rs.3.rs-2487057/v1
Bandwidth Allocation for eMBB and mMTC Slices Based on AI-Aided Traffic Prediction
Zhang, X., Liang, K., Chen, J., & Liu, J. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-37139-4_11
Interference Nulling Using Reconfigurable Intelligent Surface
Jiang, T., Sohrabi, F., & Yu, W. (2023) · Wiley eBooks · doi:10.1002/9781119913122.ch11
Self-citationBlind Beamforming for IRS Without Channel Estimation
Shen, K., & Luo, Z.-Q. T. (2023) · Wiley eBooks · doi:10.1002/9781119913122.ch12
Elimination of Interference Analysis for RIS Element Demage
Min, S., Yu, C., Li, L., Li, Y., & Zlatanov, N. (2024) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict61637.2024.10670800
Channel Estimation for Double Intelligent Reflecting Surface Assisted MISO System in Sub-6G
Wang, L. F., Zhang, J., Shi, W., & Wang, S. (2024) · International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT) · doi:10.1109/ccpqt64497.2024.00021
Sparse Neural Precoders for Distributed Integrated Sensing and Communication Systems
Chatterjee, S., Sankar, R. S. P., & Chepuri, S. P. (2024) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf60004.2024.10942644
Precoding Algorithms for IRS Assisted MIMO Networks
Wijesinghe, S., Tsimenidis, C. C., & Mumtaz, S. (2025) · International Conference on Computer, Information and Telecommunication Systems · doi:10.1109/cits65975.2025.11099205
Location-Embedded Graph Attention Network for Channel Estimation in RIS-assisted MIMO Systems
Cheng, K., Song, X., & Jin, H. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-fall65116.2025.11309859
Pilot-driven deep learning based RIS-assisted beamforming for secrecy rate maximization
Francis, N. E., Phan, K. T., & Cheng, P. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104352
Active Sensing for Localization with Reconfigurable Intelligent Surface Based on LSTM Network
Bian, H., Zhang, J., Yu, C., Zhu, L., Yan, Y., Yu, Y., Lin, L., & Zhou, R. (2025) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp68525.2025.1010503
Learning-Based RIS-Assisted Secure Beamforming Design: A User-Scalable GNN Approach
Francis, N. E., Cheng, P., Lukito, W. D., & Gao, Y. (2025) · International Workshop on Signal Design and its Applications in Communications · doi:10.1109/iwsda67899.2025.11457406
Location-Aided GNN-Based MISO RSMA Systems With Pilot Contamination
Qi, T., Wu, Z., Hoang, D. T., & Wang, L. (2026) · IEEE Communications Letters · doi:10.1109/lcomm.2026.3702658
Adaptive Beamforming for IRS-Assisted Communications via Receiver’s Feedback
Jia, S., Wang, Y., Zhao, D., Zhang, D., Zhang, R., & Wu, Q. (2026) · IEEE Communications Letters · doi:10.1109/lcomm.2026.3704474
Pilot-Driven Implicit-CSI User Grouping and Scheduling for Wideband MU-MIMO-OFDM Systems
Ba, T. (2026) · International Conference on Signal Image Processing and Communication (ICSIPC) · doi:10.1109/icsipc69751.2026.11583997
GNN-Aided Online Calibration of Phase Shifters
Roth, I., & Lampe, L. (2025) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps68340.2025.11590896
Chan, K.-L., Chang, R. Y., & Chien, F. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587553
Secrecy Energy Efficiency for IRS-Assisted Low-Altitude Communications: A D3QN-PER Based ApproachPreprint
Gao, Y., Zhao, P., Li, Y., & Cheng, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.24183
Scalable Design for RIS-Assisted Multi-User Downlink System Empowered by RSMA Under Partial CSI
Chen, Y., Fang, Y., Peng, B., Huang, A., Li, Q., Chafii, M., & Jorswieck, E. A. (2026) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2026.3721528
Over-the-Air Interference Nulling Using Passive RIS for Two-Way K -User Interference Channel
Wang, J., Sun, J., Liao, L., Liao, X., & Liu, Y. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3725788
Jassim, O. A., Najeh, S., & Bouallègue, A. (2026) · Future Internet · doi:10.3390/fi18100522
Blind Beamforming for Intelligent Reflecting Surfaces: A Gradient Bandit ApproachPreprint
Lai, W., Li, M., & Shen, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.06565
Decentralized Graph Neural Network-Based Joint Beamforming in Multi-RIS-Aided Cell-Free Networks
Ting, W.-Y., Chang, R. Y., Chien, F., Peng, T.-Y., & Lin, P.-H. (2026) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2026-fall68024.2026.11758549
Resource Allocation for Reconfigurable Intelligent Surface assisted Wireless Communications
Abouamer, M. (2025) · UWSpace (University of Waterloo)
Gao, K., Guan, M., Wuzhou, Tanghui, & Wang, W.-Q. (2026) · International Journal of Antennas and Propagation · doi:10.1155/ijap/3349803
Metadata
- Authors
- Jiang, T., Cheng, H. V., & Yu, W.
- Affiliations
- University of Toronto (CA)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-07
- Volume
- 39
- Issue
- 7
- Pages
- 1931-1945
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3160036209
- Cited by
- 290
- References
- 42
- Citations by year
- 2026: 31 · 2025: 72 · 2024: 65 · 2023: 66 · 2022: 41 · 2021: 14
- FWCI
- 13.68
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- Funders
- Huawei Technologies Canada
- Natural Sciences and Engineering Research Council (NSERC) via the Canada Research Chairs Program
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Antenna and Metasurface Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Millimeter-Wave Propagation and Modeling
- Keywords
- reconfigurable intelligent surface, beamforming, phase shift optimization, deep neural network, graph neural networks, permutation equivariance, cellular networks, pilot overhead reduction, sum rate maximization, user location information
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.