Deep reinforcement learning autoencoder with RA-GAN and GAN

(1) Hoang-Sy Nguyen Mail (Becamex Business School, Eastern International University, Viet Nam)
(2) * Cong-Danh Huynh Mail (Thu Dau Mot University, Viet Nam)
*corresponding author

Abstract


Deep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectively. As a solution for this, we first investigate typical end-to-end learning for a communication system, Generative Adversarial Network (GAN). Then, two problems associated with GAN-based systems, the gradient vanishing and overfitting, are reviewed. Subsequently, a residual aided GAN (RA-GAN) is proposed as means to overcome these problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. Finally, the numerical results performed in MATLAB for simulation and Codelabs for training have proven that the RA-GAN scheme has near-optimal performance and outperforms the conventional GAN scheme. Throughout this case study, readers can understand the issues that would occur when deep learning is applied to a communication system and possible approaches to address them.

Keywords


Artificial neural networks; Communication systems; Reinforcement; learning-based training; Channel models

   

DOI

https://doi.org/10.26555/ijain.v8i3.896
      

Article metrics

Abstract views : 145 | PDF views : 31

   

Cite

   

Full Text

Download

References


[1] N. Samuel, T. Diskin, and A. Wiesel, “Deep MIMO Detection,” IEEE Work. Signal Process. Adv. Wirel. Commun. SPAWC, vol. 2017-July, pp. 1–5, Jun. 2017, doi: 10.1109/SPAWC.2017.8227772.

[2] H. He, C. K. Wen, S. Jin, and G. Y. Li, “Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems,” IEEE Wirel. Commun. Lett., vol. 7, no. 5, pp. 852–855, Oct. 2018, doi: 10.1109/LWC.2018.2832128.

[3] E. Nachmani, Y. Be’Ery, and D. Burshtein, “Learning to Decode Linear Codes Using Deep Learning,” 54th Annu. Allert. Conf. Commun. Control. Comput. Allert. 2016, pp. 341–346, Jul. 2016, doi: 10.48550/arxiv.1607.04793.

[4] H. Ye, G. Y. Li, and B. H. Juang, “Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems,” IEEE Wirel. Commun. Lett., vol. 7, no. 1, pp. 114–117, Feb. 2018, doi: 10.1109/LWC.2017.2757490.

[5] N. Farsad, M. Rao, and A. Goldsmith, “Deep Learning for Joint Source-Channel Coding of Text,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. 2018-April, pp. 2326–2330, Feb. 2018, doi: 10.48550/arxiv.1802.06832.

[6] Z. Qin, H. Ye, G. Y. Li, and B. H. F. Juang, “Deep learning in physical layer communications,” IEEE Wirel. Commun., vol. 26, no. 2, pp. 93–99, Apr. 2019, doi: 10.1109/MWC.2019.1800601.

[7] A. Felix, S. Cammerer, S. Dorner, J. Hoydis, and S. Ten Brink, “OFDM-Autoencoder for End-to-End Learning of Communications Systems,” IEEE Work. Signal Process. Adv. Wirel. Commun. SPAWC, vol. 2018-June, Mar. 2018, doi: 10.48550/arxiv.1803.05815.

[8] T. Wang, C. K. Wen, H. Wang, F. Gao, T. Jiang, and S. Jin, “Deep Learning for Wireless Physical Layer: Opportunities and Challenges,” China Commun., vol. 14, no. 11, pp. 92–111, Oct. 2017, doi: 10.48550/arxiv.1710.05312.

[9] F. A. Aoudia and J. Hoydis, “End-to-End Learning of Communications Systems Without a Channel Model,” Conf. Rec. - Asilomar Conf. Signals, Syst. Comput., vol. 2018-October, pp. 298–303, Feb. 2019, doi: 10.1109/ACSSC.2018.8645416.

[10] W. Yu, T. Wang, and S. Wang, “Multi-Label Learning Based Antenna Selection in Massive MIMO Systems,” IEEE Trans. Veh. Technol., vol. 70, no. 7, pp. 7255–7260, Jul. 2021, doi: 10.1109/TVT.2021.3087132.

[11] “Machine learning for 5G and beyond: From model-based to data-driven mobile wireless networks | IEEE Journals & Magazine | IEEE Xplore.” (accessed Jan. 02, 2023), doi : 10.12676/j.cc.2019.01.015.

[12] M. Singh, “Integrating Artificial Intelligence and 5G in the Era of Next-Generation Computing,” Proc. - 2021 2nd Int. Conf. Comput. Methods Sci. Technol. ICCMST 2021, pp. 24–29, 2021, doi: 10.1109/ICCMST54943.2021.00017.

[13] S. Han, I. Chih-Lin, G. Li, S. Wang, and Q. Sun, “Big Data Enabled Mobile Network Design for 5G and beyond,” IEEE Commun. Mag., vol. 55, no. 9, pp. 150–157, Jul. 2017, doi: 10.1109/MCOM.2017.1600911.

[14] S. Zhang, Y. Zhang, J. Chang, B. Wang, and W. Bai, “DNN-based Signal Detection for Underwater OTFS Systems,” 2022 IEEE/CIC Int. Conf. Commun. China, ICCC Work. 2022, pp. 348–352, 2022, doi: 10.1109/ICCCWORKSHOPS55477.2022.9896695.

[15] O. Agiv and N. Shlezinger, “Learn to Rapidly Optimize Hybrid Precoding,” IEEE Work. Signal Process. Adv. Wirel. Commun. SPAWC, vol. 2022-July, 2022, doi: 10.1109/SPAWC51304.2022.9833923.

[16] T. Diskin, U. Okun, and A. Wiesel, “Learning to Detect with Constant False Alarm Rate,” Jun. 2022, doi: 10.48550/arxiv.2206.05747.

[17] T. O’Shea and J. Hoydis, “An Introduction to Deep Learning for the Physical Layer,” IEEE Trans. Cogn. Commun. Netw., vol. 3, no. 4, pp. 563–575, Dec. 2017, doi: 10.1109/TCCN.2017.2758370.

[18] H. Ye, G. Y. Li, B. H. F. Juang, and K. Sivanesan, “Channel Agnostic End-to-End Learning based Communication Systems with Conditional GAN,” 2018 IEEE Globecom Work. GC Wkshps 2018 - Proc., Jul. 2018, doi: 10.48550/arxiv.1807.00447.

[19] M. Goutay, F. A. Aoudia, and J. Hoydis, “Deep Reinforcement Learning Autoencoder with Noisy Feedback,” Proc. - 17th Int. Symp. Model. Optim. Mobile, Ad Hoc, Wirel. Networks, WiOpt 2019, Oct. 2018, doi: 10.48550/arxiv.1810.05419.

[20] H. Ye, L. Liang, G. Y. Li, and B. H. Juang, “Deep Learning-Based End-to-End Wireless Communication Systems with Conditional GANs as Unknown Channels,” IEEE Trans. Wirel. Commun., vol. 19, no. 5, pp. 3133–3143, May 2020, doi: 10.1109/TWC.2020.2970707.

[21] T. J. O’Shea, T. Roy, N. West, and B. C. Hilburn, “Physical Layer Communications System Design Over-the-Air Using Adversarial Networks,” Eur. Signal Process. Conf., vol. 2018-September, pp. 529–532, Mar. 2018, doi: 10.48550/arxiv.1803.03145.

[22] T. J. Orshea, T. Roy, and N. West, “Approximating the Void: Learning Stochastic Channel Models from Observation with Variational Generative Adversarial Networks,” 2019 Int. Conf. Comput. Netw. Commun. ICNC 2019, pp. 681–686, May 2018, doi: 10.48550/arxiv.1805.06350.

[23] S. Dorner, M. Henninger, S. Cammerer, and S. Ten Brink, “WGAN-based Autoencoder Training Over-the-air,” IEEE Work. Signal Process. Adv. Wirel. Commun. SPAWC, vol. 2020-May, Mar. 2020, doi: 10.48550/arxiv.2003.02744.

[24] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein Generative Adversarial Networks.” PMLR, pp. 214–223, Jul. 17, 2017. Accessed: Jan. 02, 2023. [Online]. Available at : https://proceedings.mlr.press/v70/arjovsky17a.html

[25] E. Zehavi, “8-PSK Trellis Codes for a Rayleigh Channel,” IEEE Trans. Commun., vol. 40, no. 5, pp. 873–884, 1992, doi: 10.1109/26.141453.

[26] S. Dorner, S. Cammerer, J. Hoydis, and S. Ten Brink, “Deep Learning Based Communication over the Air,” IEEE J. Sel. Top. Signal Process., vol. 12, no. 1, pp. 132–143, Feb. 2018, doi: 10.1109/JSTSP.2017.2784180.

[27] F. Liang, C. Shen, and F. Wu, “An Iterative BP-CNN Architecture for Channel Decoding,” IEEE J. Sel. Top. Signal Process., vol. 12, no. 1, pp. 144–159, Feb. 2018, doi: 10.1109/JSTSP.2018.2794062.

[28] D. P. Kingma and J. L. Ba, “Adam: A Method for Stochastic Optimization,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., Dec. 2014, doi: 10.48550/arxiv.1412.6980.

[29] R. Sattiraju, A. Weinand, and H. D. Schotten, “Performance Analysis of Deep Learning based on Recurrent Neural Networks for Channel Coding,” Int. Symp. Adv. Networks Telecommun. Syst. ANTS, vol. 2018-December, Jul. 2018, doi: 10.1109/ANTS.2018.8710159.

[30] D. Wu, M. Nekovee, and Y. Wang, “An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12081 LNCS, pp. 342–354, 2020, doi: 10.1007/978-3-030-45778-5_23.

[31] A. Al-Baidhani and H. H. Fan, “Deep ensemble learning: A communications receiver over wireless fading channels,” Glob. 2019 - 7th IEEE Glob. Conf. Signal Inf. Process. Proc., Nov. 2019, doi: 10.1109/GLOBALSIP45357.2019.8969302.

[32] Q. Mao, F. Hu, and Q. Hao, “Deep learning for intelligent wireless networks: A comprehensive survey,” IEEE Commun. Surv. Tutorials, vol. 20, no. 4, pp. 2595–2621, Oct. 2018, doi: 10.1109/COMST.2018.2846401.




Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
   andri.pranolo.id@ieee.org (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0