pith. machine review for the scientific record. sign in

arxiv: 2604.22706 · v1 · submitted 2026-04-24 · 📡 eess.SP

Recognition: unknown

When AI Meets Terahertz: A Survey on the Symbiosis of Artificial Intelligence and Terahertz Networks

Chong Han , Jingting Jiang , Zhengdong Hu , Meixia Tao , Wenjun Zhang
Authors on Pith no claims yet

Pith reviewed 2026-05-08 10:16 UTC · model grok-4.3

classification 📡 eess.SP
keywords AITerahertzWireless networksSymbiosisChannel modelingNetwork optimizationSensingEdge computing
0
0 comments X

The pith

AI techniques address terahertz network challenges while terahertz bandwidth and sensing support AI operations in a mutual symbiosis.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper examines how artificial intelligence can manage the complex channel behaviors, large-scale optimization tasks, and rapid changes in terahertz wireless systems that currently block practical use. It also shows how the enormous bandwidth and precise sensing of terahertz links can supply the data volumes and speeds needed for AI model training and real-time decisions. This two-way relationship means each technology supplies what the other lacks, opening paths to integrated systems that deliver terabit speeds and advanced services together.

Core claim

AI serves as a transformative enabler to address THz challenges including intricate channel characteristics and high-dimensional optimization, while THz networks provide infrastructure for AI training, inference, and data collection, leading to mutual symbiosis.

What carries the argument

The bidirectional symbiosis in which AI supplies modeling, optimization, and decision tools for terahertz hardware and protocols while terahertz supplies ultra-wide bandwidth and high-resolution sensing to support AI workloads.

If this is right

  • AI-driven channel modeling and signal processing make terahertz hardware design and physical-layer operation feasible at scale.
  • Terahertz ultra-wide bandwidth enables faster collection and transfer of the large datasets required for AI training and inference.
  • Joint AI-THz designs support higher-layer functions such as mobile edge computing and sensing-based applications.
  • The co-evolution creates new services that combine terahertz sensing precision with AI prediction and control.
  • Open directions remain for extending the symbiosis across full protocol stacks and real-world deployments.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Integrated AI-THz systems could shorten the timeline for reliable terabit wireless links by solving channel and optimization barriers together.
  • Terahertz sensing data streams might supply continuous real-world labels that improve AI performance in wireless environments.
  • The same pairing pattern may apply to other high-frequency bands or sensing technologies that need both optimization and data infrastructure.
  • Deployment trials in varied mobility and interference conditions would show whether the claimed mutual gains persist beyond controlled settings.

Load-bearing premise

That current AI methods can reliably solve the physical-layer difficulties of terahertz waves and that terahertz links can deliver stable high-bandwidth support for AI in real dynamic settings.

What would settle it

A measurement campaign that records whether an AI-optimized terahertz link sustains multi-gigabit or terabit rates over minutes in a moving outdoor environment, or whether terahertz-collected data volumes can train and run AI models without latency or capacity shortfalls.

Figures

Figures reproduced from arXiv: 2604.22706 by Chong Han, Jingting Jiang, Meixia Tao, Wenjun Zhang, Zhengdong Hu.

Figure 1
Figure 1. Figure 1: Applications enabled by THz communications and networking. view at source ↗
Figure 2
Figure 2. Figure 2: AI solutions for THz. and data collection. Moreover, novel physical computing ar￾chitectures, such as THz diffractive neural networks, offer a low-power and near-zero-latency pathway to support intensive AI operations. Ultimately, the profound symbiosis of AI￾driven methodologies and THz networks marks a transforma￾tive paradigm shift to foster innovative solutions for future intelligent wireless systems. … view at source ↗
Figure 3
Figure 3. Figure 3: Structure of the survey. • We identify open challenges and outline future directions to further converge AI and THz communications. The remainder of this survey follows the organization in view at source ↗
Figure 4
Figure 4. Figure 4: Classification of AI techniques. breakthroughs drive the frontier toward AGI techniques, like agentic AI. The classification of AI is summarized in view at source ↗
Figure 5
Figure 5. Figure 5: Architecture of a GNN view at source ↗
Figure 6
Figure 6. Figure 6: Architecture of a classical LSTM view at source ↗
Figure 7
Figure 7. Figure 7: Flowchart of RL/DRL. clients train models locally and upload only weight parameters for global aggregation. This mechanism inherently preserves privacy and mitigates communication latency. As networks evolve toward edge intelligence paradigms, FL becomes in￾creasingly vital. For instance, FL optimizes beamforming to avoid massive local CSI exchanges [53]. Furthermore, collab￾orative knowledge from distribu… view at source ↗
Figure 8
Figure 8. Figure 8: Framework of GAN view at source ↗
Figure 9
Figure 9. Figure 9: Framework of transformer encoder transformers utilize stacked encoders and decoders to process sequences globally in parallel. Positional encodings preserve sequence order to capture complex global relationships. Con￾sequently, self-attention utilizes historical datasets to enhance predictive accuracy in communication networks. Specifically, transformers optimize beam management [80], [81] and chan￾nel est… view at source ↗
Figure 10
Figure 10. Figure 10: Hardware imperfections in THz UM-MIMO system [98] view at source ↗
Figure 11
Figure 11. Figure 11: A generic framework for GAN based channel modeling. view at source ↗
Figure 12
Figure 12. Figure 12: Near-field and far-field channel estimation based on diffusion model [138]. view at source ↗
Figure 13
Figure 13. Figure 13: Deep unfolding Networks for Beamforming. view at source ↗
Figure 14
Figure 14. Figure 14: AI-enabled MAC layer management framework. view at source ↗
Figure 15
Figure 15. Figure 15: A general framework for Q-learning based routing design. view at source ↗
Figure 16
Figure 16. Figure 16: The system architecture of ISCC framework. view at source ↗
Figure 17
Figure 17. Figure 17: Hybrid distributed learning architecture. view at source ↗
Figure 18
Figure 18. Figure 18: Future directions. requirements of massive users significantly complicate the optimization of resource allocation and routing selection for traditional methods. In this regard, AI techniques, especially RL and DRL, offer a promising solution. By enabling the system to perceive environmental states in real time and au￾tonomously learn optimal policies, these approaches facilitate intelligent and adaptive n… view at source ↗
read the original abstract

The Terahertz (THz) band (0.1-10 THz) has emerged as a critical frontier for future communication systems, offering ultra-wide bandwidths that enable Terabits-per-second (Tbps) wireless links and high-precision sensing and imaging. However, practical deployment of THz systems is hindered by unique challenges, including intricate channel characteristics, high-dimensional and large-scale optimization problems, and highly dynamic network environments. Artificial Intelligence (AI) serves as a transformative enabler to address these challenges, providing robust capabilities for precise modeling, advanced signal processing, complex optimization, real-time decision-making, and prediction, among others. Reciprocally, the unprecedented bandwidth and high-resolution sensing capabilities of THz networks provide a promising physical infrastructure for AI, facilitating training, inference, and data collection. This survey presents a systematic and comprehensive overview of AI-driven solutions across the entire THz communication network and the symbiosis of AI and THz networks. To begin with, a foundational overview of AI technologies tailored for wireless communications is presented. Subsequently, AI-based innovations are investigated, spanning from hardware design, channel modeling, physical layer optimization, up to higher-layer network protocols and advanced THz services, including mobile edge computing and sensing-empowered applications. In parallel, the capacity of THz networks to serve AI is examined, underscoring a profound paradigm shift towards a mutual symbiosis where AI and THz co-evolve and empower each other. Finally, by synthesizing these state-of-the-art advancements and identifying open research directions, this survey highlights the potential of AI in copilot with development of THz communication systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. This survey paper claims that AI and THz networks form a mutual symbiosis: AI techniques address THz-specific challenges such as intricate channel characteristics, high-dimensional optimization, and dynamic environments through modeling, signal processing, and decision-making; reciprocally, THz's ultra-wide bandwidth and high-resolution sensing enable AI training, inference, and data collection. The manuscript structures its review as an overview of AI for wireless, followed by AI applications spanning THz hardware design, channel modeling, physical-layer optimization, network protocols, and services (e.g., mobile edge computing and sensing), then examines THz as infrastructure for AI, and concludes with open research directions.

Significance. If the literature mapping is balanced and accurate, the survey would be a useful reference for the emerging intersection of AI and THz communications, synthesizing bidirectional opportunities that are typically treated separately. Its value lies in the systematic coverage from hardware to services and the explicit framing of co-evolution, which could help orient researchers toward integrated 6G designs.

major comments (1)
  1. [Abstract] Abstract and the symbiosis framing: the central claim that current AI techniques 'serve as a transformative enabler' and that THz 'provides a promising physical infrastructure' for AI workloads is presented as established by the surveyed body of work, yet the manuscript does not explicitly quantify or tabulate how many cited studies provide experimental validation versus simulation-only results in realistic THz propagation conditions; this weakens the strength of the mutual-feasibility assertion.
minor comments (2)
  1. [Abstract] The abstract and introduction could include a brief statement on the total number of references reviewed and the time window covered (e.g., up to 2024) to help readers assess completeness.
  2. [Overall structure] Figure captions and section headings would benefit from consistent use of acronyms on first use within each major section to improve readability for a broad audience.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our survey manuscript. The comment regarding the abstract and symbiosis framing has been carefully considered, and we have revised the paper to address it directly.

read point-by-point responses

  1. Referee: [Abstract] Abstract and the symbiosis framing: the central claim that current AI techniques 'serve as a transformative enabler' and that THz 'provides a promising physical infrastructure' for AI workloads is presented as established by the surveyed body of work, yet the manuscript does not explicitly quantify or tabulate how many cited studies provide experimental validation versus simulation-only results in realistic THz propagation conditions; this weakens the strength of the mutual-feasibility assertion.

    Authors: We acknowledge the referee's point that the abstract's symbiosis claims would be strengthened by an explicit breakdown of validation types across the cited literature. As a survey, the manuscript synthesizes opportunities from a wide body of work, many of which are simulation-based due to the emerging nature of THz hardware; however, we agree that readers would benefit from clearer context on the proportion of experimental validations, particularly those under realistic propagation conditions. In the revised manuscript, we will add a new table (or subsection in the introduction) that categorizes key referenced studies by validation method (e.g., pure simulation, hardware-in-the-loop, or real-world experiments) and notes on THz-specific realism. This will directly support the mutual-feasibility assertions without altering the core framing, which remains grounded in the collective advancements reviewed. revision: yes

Circularity Check

0 steps flagged

No significant circularity; survey synthesis of external literature

full rationale

This is a literature survey whose central claim is a synthesis of prior external work on AI techniques for THz challenges and THz capabilities for AI workloads. No original derivations, equations, fitted parameters, or predictions are advanced that could reduce to inputs by construction. The argument rests on the accuracy of the cited body of work rather than self-referential loops, self-citations as load-bearing premises, or ansatzes smuggled in. The derivation chain is self-contained as a mapping exercise with no internal reduction to fitted or renamed results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a survey paper that aggregates existing research without introducing new free parameters, axioms, or invented entities.

pith-pipeline@v0.9.0 · 5599 in / 974 out tokens · 37396 ms · 2026-05-08T10:16:12.667200+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

285 extracted references · 17 canonical work pages · 3 internal anchors

  1. [1]

    Terahertz band communication: An old problem revisited and research directions for the next decade,

    I. F. Akyildizet al., “Terahertz band communication: An old problem revisited and research directions for the next decade,”IEEE Trans. Commun., vol. 70, no. 6, pp. 4250–4285, 2022

    2022

  2. [2]

    Toward 6G networks: Use Cases and Technologies,

    M. Giordani, M. Polese, M. Mezzavilla, S. Rangan, and M. Zorzi, “Toward 6G networks: Use Cases and Technologies,”IEEE Commun. Mag., vol. 58, no. 3, pp. 55–61, 2020

    2020

  3. [3]

    6G wireless systems: Vision, requirements, chal- lenges, insights, and opportunities,

    H. Tatariaet al., “6G wireless systems: Vision, requirements, chal- lenges, insights, and opportunities,”Proc. IEEE, vol. 109, no. 7, pp. 1166–1199, 2021

    2021

  4. [4]

    A vision of 6G wireless systems: Applications, trends, technologies, and open research problems,

    W. Saad, M. Bennis, and M. Chen, “A vision of 6G wireless systems: Applications, trends, technologies, and open research problems,”IEEE Netw., vol. 34, no. 3, pp. 134–142, 2019

    2019

  5. [5]

    IMT Vision—Framework and Overall Objectives of the Future Devel- opment of IMT for 2020 and Beyond,

    “IMT Vision—Framework and Overall Objectives of the Future Devel- opment of IMT for 2020 and Beyond,” Rec. M.2083, Int. Telecommun. Union, Geneva, Switzerland, 2015

    2020

  6. [6]

    Combating the Distance Problem in the Millimeter Wave and Terahertz Frequency Bands,

    I. F. Akyildiz, C. Han, and S. Nie, “Combating the Distance Problem in the Millimeter Wave and Terahertz Frequency Bands,”IEEE Commun. Mag., vol. 56, no. 6, pp. 102–108, 2018

    2018

  7. [7]

    Terahertz Wireless Communications for 2030 and Beyond: A Cutting-Edge Frontier,

    Z. Chenet al., “Terahertz Wireless Communications for 2030 and Beyond: A Cutting-Edge Frontier,”IEEE Commun. Mag., vol. 59, no. 11, pp. 66–72, 2021

    2030

  8. [8]

    Physical layer signal processing for XR communications and systems,

    Y . Wu, M. Xu, G. Zhai, and W. Zhang, “Physical layer signal processing for XR communications and systems,”Sci. China Inf. Sci., vol. 67, no. 12, p. 221301, 2024

    2024

  9. [9]

    Joint devices and IRSs association for terahertz communications in Industrial IoT networks,

    M. Rahim, G. Kaddoum, and T. N. Do, “Joint devices and IRSs association for terahertz communications in Industrial IoT networks,” IEEE Trans. Green Commun. Networking, vol. 8, no. 1, pp. 375–390, 2023

    2023

  10. [10]

    Use Cases for Terahertz Communications: An Industrial Perspective,

    T. Zugnoet al., “Use Cases for Terahertz Communications: An Industrial Perspective,”IEEE Wirel. Commun., vol. 32, no. 1, pp. 90– 98, 2025

    2025

  11. [11]

    Thz ISAC: A Physical-Layer [p]erspective of Terahertz Integrated Sensing and Communication,

    C. Han, Y . Wu, Z. Chen, Y . Chen, and G. Wang, “Thz ISAC: A Physical-Layer [p]erspective of Terahertz Integrated Sensing and Communication,”IEEE Commun. Mag., 2023

    2023

  12. [12]

    Terahertz aerospace communications: enabling technologies and future directions,

    W. Gao, C. Han, Y . Chen, Y . He, and W. Zhang, “Terahertz aerospace communications: enabling technologies and future directions,”Sci. China Inf. Sci., vol. 68, no. 12, p. 220302, 2025. 25

    2025

  13. [13]

    Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks,

    A. Liao, Z. Gao, D. Wang, H. Wang, H. Yin, D. W. K. Ng, and M.-S. Alouini, “Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks,”IEEE J. Sel. Areas Commun., vol. 39, no. 6, pp. 1741–1767, 2021

    2021

  14. [14]

    Terahertz-Band Near-Space Communications: From a Physical-Layer Perspective,

    T. Mao, L. Zhang, Z. Xiao, Z. Han, and X.-G. Xia, “Terahertz-Band Near-Space Communications: From a Physical-Layer Perspective,” IEEE Commun. Mag., vol. 62, no. 2, pp. 110–116, 2024

    2024

  15. [15]

    IAB vs. RIS: Performance-Cost Tradeoffs in 5G/6G Systems with Multicast and Unicast Traffic in Roadside Deployments,

    O. Chukhno, D. Moltchanov, G. Brancati, S. Pizzi, A. Molinaro, and G. Araniti, “IAB vs. RIS: Performance-Cost Tradeoffs in 5G/6G Systems with Multicast and Unicast Traffic in Roadside Deployments,” IEEE Trans. Mob. Comput., 2025

    2025

  16. [16]

    Joint beamforming-power-bandwidth allocation in terahertz NOMA networks,

    X. Zhang, C. Han, and X. Wang, “Joint beamforming-power-bandwidth allocation in terahertz NOMA networks,” inProc. IEEE Int. Conf. Sens., Commun., Netw. (SECON), 2019, pp. 1–9

    2019

  17. [17]

    Molecular absorption effect: A double-edged sword of terahertz communications,

    C. Han, W. Gao, N. Yang, and J. M. Jornet, “Molecular absorption effect: A double-edged sword of terahertz communications,”IEEE Wirel. Commun., vol. 30, no. 4, pp. 140–146, 2022

    2022

  18. [18]

    A study of diffuse scattering in massive mimo channels at terahertz frequencies,

    F. Sheikh, Y . Gao, and T. Kaiser, “A study of diffuse scattering in massive mimo channels at terahertz frequencies,”IEEE Trans. Antennas Propag., vol. 68, no. 2, pp. 997–1008, 2019

    2019

  19. [19]

    Spatial modulation for terahertz com- munication systems with hardware impairments,

    T. Mao, Q. Wang, and Z. Wang, “Spatial modulation for terahertz com- munication systems with hardware impairments,”IEEE Transactions on Vehicular Technology, vol. 69, no. 4, pp. 4553–4557, 2020

    2020

  20. [20]

    Cross far-and near- field wireless communications in terahertz ultra-large antenna array systems,

    C. Han, Y . Chen, L. Yan, Z. Chen, and L. Dai, “Cross far-and near- field wireless communications in terahertz ultra-large antenna array systems,”IEEE Wirel. Commun., vol. 31, no. 3, pp. 148–154, 2024

    2024

  21. [21]

    Capacity and outage of terahertz communications with user micro-mobility and beam misalignment,

    V . Petrov, D. Moltchanov, Y . Koucheryavy, and J. M. Jornet, “Capacity and outage of terahertz communications with user micro-mobility and beam misalignment,”IEEE Trans. Veh. Technol., vol. 69, no. 6, pp. 6822–6827, 2020

    2020

  22. [22]

    Graph Neural Network Aided Deep Reinforce- ment Learning for Resource Allocation in Dynamic Terahertz UA V Networks,

    Z. Hu and C. Han, “Graph Neural Network Aided Deep Reinforce- ment Learning for Resource Allocation in Dynamic Terahertz UA V Networks,”arXiv preprint arXiv:2505.04981, 2025

    work page arXiv 2025

  23. [23]

    Teranets: Ultra-broadband communication networks in the terahertz band,

    I. F. Akyildiz, J. M. Jornet, and C. Han, “Teranets: Ultra-broadband communication networks in the terahertz band,”IEEE Wireless Com- munications, vol. 21, no. 4, pp. 130–135, 2014

    2014

  24. [24]

    An Overview for Designing 6G Networks: Technologies, Spectrum Management, Enhanced Air Interface, and AI/ML Optimization,

    D. Sharma, V . Tilwari, and S. Pack, “An Overview for Designing 6G Networks: Technologies, Spectrum Management, Enhanced Air Interface, and AI/ML Optimization,”IEEE Internet Things J., vol. 12, no. 6, pp. 6133–6157, 2025

    2025

  25. [25]

    Deep learning techniques for advancing 6G communications in the physical layer,

    S. Zhang, J. Liu, T. K. Rodrigues, and N. Kato, “Deep learning techniques for advancing 6G communications in the physical layer,” IEEE Wirel. Commun., vol. 28, no. 5, pp. 141–147, 2021

    2021

  26. [26]

    Artificial intelligence for wireless physical-layer technologies (AI4PHY): A comprehensive survey,

    N. Ye, S. Miao, J. Pan, Q. Ouyang, X. Li, and X. Hou, “Artificial intelligence for wireless physical-layer technologies (AI4PHY): A comprehensive survey,”IEEE Trans. Cogn. Commun. Netw., vol. 10, no. 3, pp. 729–755, 2024

    2024

  27. [27]

    Survey on machine learning for intelligent end-to-end communication toward 6G: From network access, routing to traffic control and streaming adaption,

    F. Tang, B. Mao, Y . Kawamoto, and N. Kato, “Survey on machine learning for intelligent end-to-end communication toward 6G: From network access, routing to traffic control and streaming adaption,”IEEE Commun. Surveys Tuts., vol. 23, no. 3, pp. 1578–1598, 2021

    2021

  28. [28]

    Overview of AI and communication for 6G network: fundamentals, challenges, and future research opportunities,

    Q. Cuiet al., “Overview of AI and communication for 6G network: fundamentals, challenges, and future research opportunities,”Sci. China Inf. Sci., vol. 68, no. 7, p. 171301, 2025

    2025

  29. [29]

    Toward a 6G AI-native air interface,

    J. Hoydis, F. A. Aoudia, A. Valcarce, and H. Viswanathan, “Toward a 6G AI-native air interface,”arXiv preprint arXiv:2012.08285, 2020

    work page arXiv 2012

  30. [30]

    NVIDIA AI Aerial: AI-Native Wireless Com- munications,

    K. Cohen-Araziet al., “NVIDIA AI Aerial: AI-Native Wireless Com- munications,”arXiv preprint arXiv:2510.01533, 2025

    work page arXiv 2025

  31. [31]

    Wireless Large AI Model: Shaping the AI-Native Future of 6G and Beyond

    F. Zhuet al., “Wireless large AI model: Shaping the AI-native future of 6G and beyond,”arXiv preprint arXiv:2504.14653, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  32. [32]

    Machine learning: A catalyst for THz wireless networks,

    A.-A. A. Boulogeorgos, E. Yaqub, M. Di Renzo, A. Alexiou, R. Desai, and R. Klinkenberg, “Machine learning: A catalyst for THz wireless networks,”Front. Commun. Netw., vol. 2, p. 704546, 2021

    2021

  33. [33]

    Machine learning for millimeter wave and terahertz beam management: A survey and open challenges,

    M. Q. Khan, A. Gaber, P. Schulz, and G. Fettweis, “Machine learning for millimeter wave and terahertz beam management: A survey and open challenges,”IEEE Access, vol. 11, pp. 11 880–11 902, 2023

    2023

  34. [34]

    Terahertz meets AI: The state of the art,

    A. Farhad and J.-Y . Pyun, “Terahertz meets AI: The state of the art,” Sensors, vol. 23, no. 11, p. 5034, 2023

    2023

  35. [35]

    AI and deep learning for THz ultra-massive MIMO: From model-driven approaches to foundation models,

    W. Yu, H. He, S. Song, J. Zhang, L. Dai, L. Zheng, and K. B. Letaief, “AI and deep learning for THz ultra-massive MIMO: From model-driven approaches to foundation models,”arXiv preprint arXiv:2412.09839, 2024

    work page arXiv 2024

  36. [36]

    Terahertz Communications for 6G and Beyond Wireless Networks: Challenges, Key Advancements, and Opportunities,

    A. Shafie, N. Yang, C. Han, J. M. Jornet, M. Juntti, and T. K ¨urner, “Terahertz Communications for 6G and Beyond Wireless Networks: Challenges, Key Advancements, and Opportunities,”IEEE Netw., vol. 37, no. 3, pp. 162–169, 2023

    2023

  37. [37]

    Deep-learning- based millimeter-wave massive MIMO for hybrid precoding,

    H. Huang, Y . Song, J. Yang, G. Gui, and F. Adachi, “Deep-learning- based millimeter-wave massive MIMO for hybrid precoding,”IEEE Trans. Veh. Technol., vol. 68, no. 3, pp. 3027–3032, 2019

    2019

  38. [38]

    Simultaneous learning and inferencing of DNN-based mmWave massive MIMO channel estimation in IoT systems with unknown nonlinear distortion,

    X. Zheng and V . K. Lau, “Simultaneous learning and inferencing of DNN-based mmWave massive MIMO channel estimation in IoT systems with unknown nonlinear distortion,”IEEE Internet Things J., vol. 9, no. 1, pp. 783–799, 2021

    2021

  39. [39]

    Deep learning for mmWave beam and blockage prediction using sub-6 GHz channels,

    M. Alrabeiah and A. Alkhateeb, “Deep learning for mmWave beam and blockage prediction using sub-6 GHz channels,”IEEE Trans. Commun., vol. 68, no. 9, pp. 5504–5518, 2020

    2020

  40. [40]

    Distributed DNN Based User Association and Re- source Optimization in mmWave Networks,

    H. Zhang, H. Zhang, W. Huangfu, W. Liu, J. Dong, K. Long, and A. Nallanathan, “Distributed DNN Based User Association and Re- source Optimization in mmWave Networks,” inProc. IEEE Global Commun. Conf. (GLOBECOM). IEEE, 2019, pp. 1–5

    2019

  41. [41]

    Deep learning approach for optimal localization using an mm-wave sensor,

    B. Amjadet al., “Deep learning approach for optimal localization using an mm-wave sensor,”IEEE Trans. Instrum. Meas., vol. 72, pp. 1–15, 2023

    2023

  42. [42]

    Deep CNN-based channel estimation for mmWave massive MIMO systems,

    P. Dong, H. Zhang, G. Y . Li, I. S. Gaspar, and N. NaderiAlizadeh, “Deep CNN-based channel estimation for mmWave massive MIMO systems,”IEEE J. Sel. Topics Signal Process., vol. 13, no. 5, pp. 989– 1000, 2019

    2019

  43. [43]

    CNN-based precoder and combiner design in mmWave MIMO systems,

    A. M. Elbir, “CNN-based precoder and combiner design in mmWave MIMO systems,”IEEE Commun. Lett., vol. 23, no. 7, pp. 1240–1243, 2019

    2019

  44. [44]

    CNN based hybrid pre- coding for mmWave MIMO systems with adaptive switching module and phase modulation array,

    Y . Hei, C. Liu, W. Li, L. Ma, and M. Lan, “CNN based hybrid pre- coding for mmWave MIMO systems with adaptive switching module and phase modulation array,”IEEE Trans. Wirel. Commun., vol. 21, no. 12, pp. 10 489–10 501, 2022

    2022

  45. [45]

    A comprehensive survey on graph neural networks,

    Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, “A comprehensive survey on graph neural networks,”IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 1, pp. 4–24, 2020

    2020

  46. [46]

    Graph Neural Network Empowered Wireless Communications: Fundamentals, State-of-the-Art, Challenges, and Opportunities,

    Z. Huang, Z. Wang, and Z. Han, “Graph Neural Network Empowered Wireless Communications: Fundamentals, State-of-the-Art, Challenges, and Opportunities,”IEEE Wirel. Commun., 2025

    2025

  47. [47]

    GBlinks: GNN-based beam selection and link activation for ultra-dense D2D mmWave networks,

    S. Heet al., “GBlinks: GNN-based beam selection and link activation for ultra-dense D2D mmWave networks,”IEEE Trans. Commun., vol. 70, no. 5, pp. 3451–3466, 2022

    2022

  48. [48]

    GNN-aided user association and beam selection for mmWave-integrated heterogeneous networks,

    W. Deng, Y . Liu, M. Li, and M. Lei, “GNN-aided user association and beam selection for mmWave-integrated heterogeneous networks,” IEEE Wirel. Commun. Lett., vol. 12, no. 11, pp. 1836–1840, 2023

    2023

  49. [49]

    GNN Based Resource Allocation for Digital Twin-Enhanced Multi-UA V Radar Networks,

    J. Luo, Z. Fei, X. Wang, L. Zhao, B. Li, and Y . Zhou, “GNN Based Resource Allocation for Digital Twin-Enhanced Multi-UA V Radar Networks,”IEEE Wirel. Commun. Lett., 2024

    2024

  50. [50]

    LSTM- based predictive mmWave beam tracking via sub-6 GHz channels for V2I communications,

    Y . Zhao, X. Zhang, X. Gao, K. Yang, Z. Xiong, and Z. Han, “LSTM- based predictive mmWave beam tracking via sub-6 GHz channels for V2I communications,”IEEE Trans. Commun., vol. 72, no. 10, pp. 6254–6270, 2024

    2024

  51. [51]

    A novel mmWave beam alignment approach for beyond 5G autonomous vehicle net- works,

    R. Benelmir, S. Bitam, S. Fowler, and A. Mellouk, “A novel mmWave beam alignment approach for beyond 5G autonomous vehicle net- works,”IEEE Trans. Veh. Technol., vol. 73, no. 2, pp. 1597–1610, 2023

    2023

  52. [52]

    Intelligent traffic steering in beyond 5G open RAN based on LSTM traffic prediction,

    F. Kavehmadavani, V .-D. Nguyen, T. X. Vu, and S. Chatzinotas, “Intelligent traffic steering in beyond 5G open RAN based on LSTM traffic prediction,”IEEE Trans. Wirel. Commun., vol. 22, no. 11, pp. 7727–7742, 2023

    2023

  53. [53]

    Federated dropout learning for hybrid beamforming with spatial path index modulation in multi- user mmWave-MIMO systems,

    A. M. Elbir, S. Coleri, and K. V . Mishra, “Federated dropout learning for hybrid beamforming with spatial path index modulation in multi- user mmWave-MIMO systems,” inProc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP). IEEE, 2021, pp. 8213–8217

    2021

  54. [54]

    Joint channel esti- mation and feedback for mm-Wave system using federated learning,

    L. Zhao, H. Xu, Z. Wang, X. Chen, and A. Zhou, “Joint channel esti- mation and feedback for mm-Wave system using federated learning,” IEEE Commun. Lett., vol. 26, no. 8, pp. 1819–1823, 2022

    2022

  55. [55]

    FedRec: Federated learning of universal receivers over fading channels,

    M. B. Mashhadi, N. Shlezinger, Y . C. Eldar, and D. G ¨und¨uz, “FedRec: Federated learning of universal receivers over fading channels,” inProc. IEEE Stat. Signal Process. Workshop (SSP Workshop). IEEE, 2021, pp. 576–580

    2021

  56. [56]

    Federated learning-based joint radar- communication mmWave beamtracking with imperfect CSI for V2X communications,

    S. Bhardwaj and D.-S. Kim, “Federated learning-based joint radar- communication mmWave beamtracking with imperfect CSI for V2X communications,” inProc. Int. Conf. Ubiquitous Future Netw. (ICUFN). IEEE, 2023, pp. 201–206

    2023

  57. [57]

    DRL-based beam allocation in relay-aided multi-user mmWave ve- hicular networks,

    Y . Ju, H. Wang, Y . Chen, L. Liu, T.-X. Zheng, Q. Pei, and M. Xiao, “DRL-based beam allocation in relay-aided multi-user mmWave ve- hicular networks,” inProc. IEEE Conf. Comput. Commun. Workshops (INFOCOM Workshops). IEEE, 2022, pp. 1–6

    2022

  58. [58]

    Self-organizing mmWave MIMO cell- free networks with hybrid beamforming: A hierarchical DRL-based design,

    Y . Al-Eryani and E. Hossain, “Self-organizing mmWave MIMO cell- free networks with hybrid beamforming: A hierarchical DRL-based design,”IEEE Trans. Commun., vol. 70, no. 5, pp. 3169–3185, 2022. 26

    2022

  59. [59]

    Deep reinforce- ment learning-based resource allocation in cooperative UA V-assisted wireless networks,

    P. Luong, F. Gagnon, L.-N. Tran, and F. Labeau, “Deep reinforce- ment learning-based resource allocation in cooperative UA V-assisted wireless networks,”IEEE Trans. Wirel. Commun., vol. 20, no. 11, pp. 7610–7625, 2021

    2021

  60. [60]

    Deep reinforcement learning for radio resource allocation and man- agement in next generation heterogeneous wireless networks: A sur- vey,

    A. Alwarafy, M. Abdallah, B. S. Ciftler, A. Al-Fuqaha, and M. Hamdi, “Deep reinforcement learning for radio resource allocation and man- agement in next generation heterogeneous wireless networks: A sur- vey,”arXiv preprint arXiv:2106.00574, 2021

    work page arXiv 2021

  61. [61]

    DRL-based intelligent resource allocation for diverse QoS in 5G and toward 6G vehicular networks: a comprehensive survey,

    H. T. Nguyen, M. T. Nguyen, H. T. Do, H. T. Hua, and C. V . Nguyen, “DRL-based intelligent resource allocation for diverse QoS in 5G and toward 6G vehicular networks: a comprehensive survey,”Wirel. Commun. Mob. Comput., vol. 2021, no. 1, p. 5051328, 2021

    2021

  62. [62]

    DRL-OR: Deep reinforcement learning-based online routing for multi-type service requirements,

    C. Liu, M. Xu, Y . Yang, and N. Geng, “DRL-OR: Deep reinforcement learning-based online routing for multi-type service requirements,” in Proc. IEEE Conf. Comput. Commun. (INFOCOM), 2021, pp. 1–10

    2021

  63. [63]

    DRSIR: A deep reinforcement learning approach for routing in software-defined networking,

    D. M. Casas-Velasco, O. M. C. Rendon, and N. L. da Fonseca, “DRSIR: A deep reinforcement learning approach for routing in software-defined networking,”IEEE Trans. Netw. Serv. Manag., vol. 19, no. 4, pp. 4807– 4820, 2021

    2021

  64. [64]

    QTCP: Adaptive congestion control with reinforcement learning,

    W. Li, F. Zhou, K. R. Chowdhury, and W. Meleis, “QTCP: Adaptive congestion control with reinforcement learning,”IEEE Trans. Netw. Sci. Eng., vol. 6, no. 3, pp. 445–458, 2018

    2018

  65. [65]

    Deep Q-network based beam tracking for mobile millimeter-wave communications,

    H. Park, J. Kang, S. Lee, J. W. Choi, and S. Kim, “Deep Q-network based beam tracking for mobile millimeter-wave communications,” IEEE Trans. Wirel. Commun., vol. 22, no. 2, pp. 961–971, 2022

    2022

  66. [66]

    Matching-aided-learning resource allocation for dy- namic offloading in mmWave MEC system,

    Z. Zhaoet al., “Matching-aided-learning resource allocation for dy- namic offloading in mmWave MEC system,”IEEE Trans. Wirel. Commun., vol. 22, no. 11, pp. 7580–7591, 2023

    2023

  67. [67]

    Proximal Policy Optimization Algorithms

    J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Prox- imal policy optimization algorithms,”arXiv preprint arXiv:1707.06347, 2017

    work page internal anchor Pith review arXiv 2017

  68. [68]

    Computation offloading and resource allocation in MEC- enabled integrated aerial-terrestrial vehicular networks: A reinforce- ment learning approach,

    N. Waqar, S. A. Hassan, A. Mahmood, K. Dev, D.-T. Do, and M. Gidlund, “Computation offloading and resource allocation in MEC- enabled integrated aerial-terrestrial vehicular networks: A reinforce- ment learning approach,”IEEE Trans. Intell. Transp. Syst., vol. 23, no. 11, pp. 21 478–21 491, 2022

    2022

  69. [69]

    Cooperative task offloading for mobile edge computing based on multi-agent deep reinforcement learning,

    J. Yang, Q. Yuan, S. Chen, H. He, X. Jiang, and X. Tan, “Cooperative task offloading for mobile edge computing based on multi-agent deep reinforcement learning,”IEEE Trans. Netw. Serv. Manag., vol. 20, no. 3, pp. 3205–3219, 2023

    2023

  70. [70]

    Co- operative UA V resource allocation and task offloading in hierarchical aerial computing systems: A MAPPO-based approach,

    H. Kang, X. Chang, J. Mi ˇsi´c, V . B. Mi ˇsi´c, J. Fan, and Y . Liu, “Co- operative UA V resource allocation and task offloading in hierarchical aerial computing systems: A MAPPO-based approach,”IEEE Internet Things J., vol. 10, no. 12, pp. 10 497–10 509, 2023

    2023

  71. [71]

    Learning internal representations by error propagation,

    D. E. Rumelhartet al., “Learning internal representations by error propagation,” 1985

    1985

  72. [72]

    Deep autoencoder based CSI feedback with feedback errors and feedback delay in FDD massive MIMO systems,

    Y . Jang, G. Kong, M. Jung, S. Choi, and I.-M. Kim, “Deep autoencoder based CSI feedback with feedback errors and feedback delay in FDD massive MIMO systems,”IEEE Wirel. Commun. Lett., vol. 8, no. 3, pp. 833–836, 2019

    2019

  73. [73]

    A new approach for an end-to-end communication system using variational auto-encoder (V AE),

    M. A. Alawad, M. Q. Hamdan, K. A. Hamdi, C. H. Foh, and A. U. Quddus, “A new approach for an end-to-end communication system using variational auto-encoder (V AE),” inProc. IEEE Global Commun. Conf. (GLOBECOM). IEEE, 2022, pp. 5159–5164

    2022

  74. [74]

    Generative adversarial nets,

    I. J. Goodfellowet al., “Generative adversarial nets,”Adv. Neural Inf. Process. Syst., vol. 27, 2014

    2014

  75. [75]

    Distributed generative ad- versarial networks for mmWave channel modeling in wireless UA V networks,

    Q. Zhang, A. Ferdowsi, and W. Saad, “Distributed generative ad- versarial networks for mmWave channel modeling in wireless UA V networks,” inProc. IEEE Int. Conf. Commun. (ICC), 2021, pp. 1–6

    2021

  76. [76]

    Generative neural network channel modeling for millimeter-wave UA V communication,

    W. Xia, S. Rangan, M. Mezzavilla, A. Lozano, G. Geraci, V . Semkin, and G. Loianno, “Generative neural network channel modeling for millimeter-wave UA V communication,”IEEE Trans. Wirel. Commun., vol. 21, no. 11, pp. 9417–9431, 2022

    2022

  77. [77]

    Wideband channel estimation with a generative adversarial network,

    E. Balevi and J. G. Andrews, “Wideband channel estimation with a generative adversarial network,”IEEE Trans. Wirel. Commun., vol. 20, no. 5, pp. 3049–3060, 2021

    2021

  78. [78]

    Over-the-air design of GAN training for mmWave MIMO channel estimation,

    A. S. Doshi, M. Gupta, and J. G. Andrews, “Over-the-air design of GAN training for mmWave MIMO channel estimation,”IEEE J. Sel. Areas Inf. Theory, vol. 3, no. 3, pp. 557–573, 2022

    2022

  79. [79]

    Attention is all you need,

    A. Vaswaniet al., “Attention is all you need,”Adv. Neural Inf. Process. Syst., vol. 30, 2017

    2017

  80. [80]

    Multi-modal transformer and reinforcement learning-based beam management,

    M. Ghassemi, H. Zhang, A. Afana, A. B. Sediq, and M. Erol- Kantarci, “Multi-modal transformer and reinforcement learning-based beam management,”IEEE Netw. Lett., 2024

    2024

Showing first 80 references.