skip to main content
10.1145/3565287.3610281acmconferencesArticle/Chapter ViewAbstractPublication PagesmobihocConference Proceedingsconference-collections
research-article
Public Access

AirFC: Designing Fully Connected Layers for Neural Networks with Wireless Signals

Published: 16 October 2023 Publication History

Abstract

This paper proposes and experimentally validates a new paradigm for computing with wireless signals over-the-air (OTA). It demonstrates the first fully connected (FC) neural network (NN) constructed entirely using channel propagation and signal interference principles. Our design is based on architecting the desired linear operation of an FC layer through the superposition of signals emitted from multiple transmitters and received at a single receiver, similar to multiple input single output (MISO) systems. Our design takes into account several practical considerations, such as the impact of multiple subcarriers, the number of transmit antennas, and the changing wireless channel. The key outcome of our work is developing a principled methodology that transforms a given trained digital FC NN into its OTA equivalent. This novel computational paradigm, which we call AirFC, allows us to run NN tasks without compute-specific hardware during tests. We validate our design using 9 time-synchronized software-defined radios (SDRs) available on the ORBIT testbed, emulating a 16 antenna array. We use the MNIST dataset as input to our wireless FC NN and demonstrate classification with 92.61% accuracy, which proves that our NN with OTA FC layers performs similar to the conventional, all-digital version with an accuracy decrease of only 0.73%.

References

[1]
Q. Pu, S. Gupta, S. Gollakota, and S. Patel, "Whole-home gesture recognition using wireless signals," in Proceedings of the 19th Annual International Conference on Mobile Computing Networking, ser. MobiCom '13, NY, USA, 2013, p. 27--38.
[2]
H. X. Nguyen, R. Trestian, D. To, and M. Tatipamula, "Digital twin for 5g and beyond," IEEE Communications Magazine, vol. 59, no. 2, pp. 10--15, 2021.
[3]
X. Shuai, Y. Shen, Y. Tang, S. Shi, L. Ji, and G. Xing, "Millieye: A lightweight mmwave radar and camera fusion system for robust object detection," ser. IoTDI '21, NY, USA, 2021, p. 145--157.
[4]
T. Wild, V. Braun, and H. Viswanathan, "Joint design of communication and sensing for beyond 5g and 6g systems," IEEE Access, pp. 30 845--30 857, 2021.
[5]
C. Chaccour, W. Saad, O. Semiari, M. Bennis, and P. Popovski, "Joint sensing and communication for situational awareness in wireless thz systems," in ICC 2022 - IEEE International Conference on Communications, Seoul, South Korea, 2022.
[6]
M. Goldenbaum, H. Boche, and S. Stańczak, "Harnessing interference for analog function computation in wireless sensor networks," IEEE Transactions on Signal Processing, vol. 61, no. 20, pp. 4893--4906, 2013.
[7]
G. Zhu, J. Xu, K. Huang, and S. Cui, "Over-the-air computing for wireless data aggregation in massive iot," IEEE Wireless Communications, pp. 57--65, 2021.
[8]
K. Yang, T. Jiang, Y. Shi, and Z. Ding, "Federated learning via over-the-air computation," Trans. Wireless. Comm., vol. 19, no. 3, p. 2022--2035, mar 2020.
[9]
I. F. Akyildiz and J. M. Jornet, "Realizing ultra-massive mimo (1024×1024) communication in the (0.06-10) terahertz band," Nano Commun. Networks, 2016.
[10]
S. Abadal, E. Alarcón, A. Cabellos-Aparicio, M. C. Lemme, and M. Nemirovsky, "Graphene-enabled wireless communication for massive multicore architectures," IEEE Communications Magazine, vol. 51, no. 11, pp. 137--143, 2013.
[11]
S. Deb, K. Chang, X. Yu, S. P. Sah, M. Cosic, A. Ganguly, P. P. Pande, B. Belzer, and D. Heo, "Design of an energy-efficient cmos-compatible noc architecture with millimeter-wave wireless interconnects," IEEE Transactions on Computers, vol. 62, no. 12, pp. 2382--2396, 2013.
[12]
L. Ju, B. Geng, J. S. A. Horng, Çağlar Girit, M. C. Martin, Z. Hao, H. A. Bechtel, X. Liang, A. Zettl, Y. R. Shen, and F. Wang, "Graphene plasmonics for tunable terahertz metamaterials." Nature nanotechnology, vol. 6 10, pp. 630--4, 2011.
[13]
ETSI, "5g; study on new radio (nr) access technology (3gpp tr 38.912 version 14.0.0 release 14)," May 2017. [Online]. Available: https://www.etsi.org/deliver/etsi_tr/138900_138999/138912/14.00.00_60/tr_138912v140000p.pdf
[14]
F. Mehmeti and C. Rosenberg, "How expensive is consistency? performance analysis of consistent rate provisioning to mobile users in cellular networks," IEEE Transactions on Mobile Computing, vol. 18, no. 5, pp. 1098--1115, 2018.
[15]
L. Bonati, P. Johari, M. Polese, S. D'Oro, S. Mohanti, M. Tehrani-Moayyed, D. Villa, S. Shrivastava, C. Tassie, K. Yoder et al., "Colosseum: Large-scale wireless experimentation through hardware-in-the-loop network emulation," in 2021 IEEE International Symposium on DySPAN), 2021, pp. 105--113.
[16]
srsRAN Project, "Open-source 4g/5g software-radio suites." [Online]. Available: https://www.srsran.com/
[17]
H. Zhang, M. Gu, X. Jiang, J. Thompson, H. Cai, S. Paesani, R. Santagati, A. Laing, Y. Zhang, M. Yung et al., "An optical neural chip for implementing complex-valued neural network," Nature Communications, vol. 12, no. 1, pp. 1--11, 2021.
[18]
K. Alemdar, D. Varshney, S. Mohanti, U. Muncuk, and K. Chowdhury, "Rfclock: Timing, phase and frequency synchronization for distributed wireless networks," ser. MobiCom '21, 2021, p. 15--27.
[19]
L. Deng, "The mnist database of handwritten digit images for machine learning research," IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 141--142, 2012.
[20]
L. Lu, G. Y. Li, A. L. Swindlehurst, A. Ashikhmin, and R. Zhang, "An overview of massive mimo: Benefits and challenges," IEEE journal of selected topics in signal processing, vol. 8, no. 5, pp. 742--758, 2014.
[21]
D. Raychaudhuri, I. Seskar, M. Ott, S. Ganu, K. Ramachandran, H. Kremo, R. Siracusa, H. Liu, and M. Singh, "Overview of the orbit radio grid testbed for evaluation of next-generation wireless network protocols," IEEE Wireless Communications and Networking Conference, vol. 3, p. 1664--1669, 2005.
[22]
E. Research, "Usrp x310," https://www.ettus.com/all-products/x310-kit/.
[23]
E. Research, "Octoclock-g cda-2990," https://www.ettus.com/all-products/octoclock-g/.
[24]
Z. Xinyu, "Analysis of m-sequence and gold-sequence in cdma system," ICCSN, no. 1, p. 466--468, 2011.
[25]
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, pp. 2278--2324, 1998.
[26]
M. W. Matthès, Y. Bromberg, J. de Rosny, and S. M. Popoff, "Learning and avoiding disorder in multimode fibers," Phys. Rev. X, vol. 11, p. 021060, Jun 2021.
[27]
D. Roy and G. Reus-Muns, "Implementation of Neural Network Training for AirFC project," https://github.com/debashriroy/AirFC_MNIST, 2022.
[28]
C. Trabelsi, O. Bilaniuk, Y. Zhang, D. Serdyuk, S. Subramanian, J. F. Santos, S. Mehri, N. Rostamzadeh, Y. Bengio, and C. J. Pal, "Deep complex networks," in International Conference on Learning Representations, 2018.
[29]
"Ieee standard for information technology-telecommunications and information exchange between systems local and metropolitan area networks-specific requirements part 11: Wireless lan medium access control (mac) and physical layer (phy) specifications amendment 1: Enhancements for high-efficiency wlan," IEEE Std 802.11ax-2021 (Amendment to IEEE Std 802.11-2020), pp. 1--767, 2021.
[30]
D. Vasisht, S. Kumar, H. Rahul, and D. Katabi, "Eliminating channel feedback in next-generation cellular networks," in Proceedings of the 2016 ACM SIGCOMM Conference, ser. SIGCOMM '16. New York, NY, USA: Association for Computing Machinery, 2016, p. 398--411.
[31]
A. Singh, M. Andrello, N. Thawdar, and J. M. Jornet, "Design and operation of a graphene-based plasmonic nano-antenna array for communication in the terahertz band," IEEE Journal on Selected Areas in Communications, vol. 38, no. 9, pp. 2104--2117, 2020.
[32]
C. Han and Y. Chen, "Propagation modeling for wireless communications in the terahertz band," IEEE Communications Magazine, vol. 56, no. 6, pp. 96--101, 2018.
[33]
Y. Wu, J. Kokkoniemi, C. Han, and M. Juntti, "Interference and coverage analysis for terahertz networks with indoor blockage effects and line-of-sight access point association," IEEE TWC, vol. 20, no. 3, pp. 1472--1486, 2021.
[34]
P. Sen, V. Ariyarathna, A. Madanayake, and J. M. Jornet, "A versatile experimental testbed for ultrabroadband communication networks above 100 ghz," Computer Networks, vol. 193, p. 108092, 2021.
[35]
Y. Koda, K. Yamamoto, T. Nishio, and M. Morikura, "Differentially private aircomp federated learning with power adaptation harnessing receiver noise," in GLOBECOM 2020-2020 IEEE Global Communications Conference, 2020, pp. 1--6.
[36]
D. Wen, G. Zhu, and K. Huang, "Reduced-dimension design of mimo aircomp for data aggregation in clustered iot networks," in IEEE GLOBECOM, 2019, pp. 1--6.
[37]
H. Hellström, V. Fodor, and C. Fischione, "Over-the-air federated learning with retransmissions," in IEEE SPAWC, 2021, pp. 291--295.
[38]
O. Abari, H. Rahul, and D. Katabi, "Over-the-air function computation in sensor networks," arXiv preprint arXiv:1612.02307, 2016.
[39]
G. Zhu, L. Chen, and K. Huang, "Mimo over-the-air computation: Beamforming optimization on the grassmann manifold," in IEEE GLOBECOM, 2018, pp. 1--6.
[40]
J. Kendall, R. Pantone, K. Manickavasagam, Y. Bengio, and B. Scellier, "Training end-to-end analog neural networks with equilibrium propagation," arXiv, 2020.
[41]
T. W. Hughes, I. A. Williamson, M. Minkov, and S. Fan, "Wave physics as an analog recurrent neural network," Science advances, vol. 5, no. 12, p. eaay6946, 2019.
[42]
S. G. Sanchez, G. Reus-Muns, C. Bocanegra, Y. Li, U. Muncuk, Y. Naderi, Y. Wang, S. Ioannidis, and K. R. Chowdhury, "Airnn: Over-the-air computation for neural networks via reconfigurable intelligent surfaces," IEEE/ACM Transactions on Networking, pp. 1--0, 2022.

Index Terms

  1. AirFC: Designing Fully Connected Layers for Neural Networks with Wireless Signals

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      MobiHoc '23: Proceedings of the Twenty-fourth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing
      October 2023
      621 pages
      ISBN:9781450399265
      DOI:10.1145/3565287
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 16 October 2023

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. over-the-air
      2. analog computation
      3. fully connected layer
      4. neural networks
      5. multiple-input single-output channels

      Qualifiers

      • Research-article

      Funding Sources

      Conference

      MobiHoc '23
      Sponsor:

      Acceptance Rates

      Overall Acceptance Rate 296 of 1,843 submissions, 16%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 255
        Total Downloads
      • Downloads (Last 12 months)161
      • Downloads (Last 6 weeks)30
      Reflects downloads up to 22 Feb 2025

      Other Metrics

      Citations

      View Options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Login options

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media