Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Auto-CsiNet: Scenario-customized Automatic Neural Network Architecture Generation for Massive MIMO CSI Feedback (2311.15950v1)

Published 27 Nov 2023 in cs.IT, cs.AI, and math.IT

Abstract: Deep learning has revolutionized the design of the channel state information (CSI) feedback module in wireless communications. However, designing the optimal neural network (NN) architecture for CSI feedback can be a laborious and time-consuming process. Manual design can be prohibitively expensive for customizing NNs to different scenarios. This paper proposes using neural architecture search (NAS) to automate the generation of scenario-customized CSI feedback NN architectures, thereby maximizing the potential of deep learning in exclusive environments. By employing automated machine learning and gradient-descent-based NAS, an efficient and cost-effective architecture design process is achieved. The proposed approach leverages implicit scene knowledge, integrating it into the scenario customization process in a data-driven manner, and fully exploits the potential of deep learning for each specific scenario. To address the issue of excessive search, early stopping and elastic selection mechanisms are employed, enhancing the efficiency of the proposed scheme. The experimental results demonstrate that the automatically generated architecture, known as Auto-CsiNet, outperforms manually-designed models in both reconstruction performance (achieving approximately a 14% improvement) and complexity (reducing it by approximately 50%). Furthermore, the paper analyzes the impact of the scenario on the NN architecture and its capacity.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. F. Tariq, M. R. A. Khandaker, K. Wong, M. A. Imran, M. Bennis, and M. Debbah, “A speculative study on 6G,” IEEE Wirel. Commun., vol. 27, no. 4, pp. 118–125, 2020.
  2. L. Lu, G. Y. Li, A. L. Swindlehurst, A. Ashikhmin, and R. Zhang, “An overview of massive MIMO: Benefits and challenges,” IEEE J. Sel. Top. Signal Process., vol. 8, no. 5, pp. 742–758, 2014.
  3. T. L. Marzetta, “Massive MIMO: an introduction,” Bell Labs Tech. J., vol. 20, pp. 11–22, 2015.
  4. R. Chataut and R. Akl, “Massive MIMO systems for 5G and beyond networks—overview, recent trends, challenges, and future research direction,” Sensors, vol. 20, no. 10, p. 2753, 2020.
  5. D. J. Love, R. W. Heath, V. K. Lau, D. Gesbert, B. D. Rao, and M. Andrews, “An overview of limited feedback in wireless communication systems,” IEEE J. Sel Areas Commun., vol. 26, no. 8, pp. 1341–1365, 2008.
  6. P. Liang, J. Fan, W. Shen, Z. Qin, and G. Y. Li, “Deep learning and compressive sensing-based CSI feedback in FDD massive MIMO systems,” IEEE Trans. Veh. Technol., vol. 69, no. 8, pp. 9217–9222, 2020.
  7. M. S. Rahman, Y.-H. Nam, J. Zhang, and J.-Y. Seol, “Linear combination codebook based CSI feedback scheme for FD-MIMO systems,” in 2015 IEEE Globecom Workshops (GC Wkshps), 2015, pp. 1–6.
  8. R. M. Dreifuerst and R. W. Heath, “Machine learning codebook design for initial access and CSI Type-II feedback in Sub-6GHz 5G NR,” IEEE Trans. Wirel. Commun., pp. 1–1, 2023.
  9. S. Liu, T. Wang, and S. Wang, “Toward intelligent wireless communications: Deep learning-based physical layer technologies,” Digit. Commun. Netw., vol. 7, no. 4, pp. 589–597, 2021.
  10. J. Hoydis, F. A. Aoudia, A. Valcarce, and H. Viswanathan, “Toward a 6G AI-Native air interface,” IEEE Commun. Mag., vol. 59, no. 5, pp. 76–81, 2021.
  11. S. Dörner, 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, 2017.
  12. H. Huang, S. Guo, G. Gui, Z. Yang, J. Zhang, H. Sari, and F. Adachi, “Deep learning for physical-layer 5G wireless techniques: Opportunities, challenges and solutions,” IEEE Wireless Communications, vol. 27, no. 1, pp. 214–222, 2020.
  13. C.-K. Wen, W.-T. Shih, and S. Jin, “Deep learning for massive MIMO CSI feedback,” IEEE Wirel. Commun. Lett., vol. 7, no. 5, pp. 748–751, 2018.
  14. J. Guo, C.-K. Wen, S. Jin, and G. Y. Li, “Overview of deep learning-based CSI feedback in massive MIMO systems,” IEEE Trans. Commun., vol. 70, no. 12, pp. 8017–8045, 2022.
  15. Y. Cui, A. Guo, and C. Song, “TransNet: Full attention network for CSI feedback in FDD massive MIMO system,” IEEE Wirel. Commun. Lett., vol. 11, no. 5, pp. 903–907, 2022.
  16. Q. Cai, C. Dong, and K. Niu, “Attention model for massive MIMO CSI compression feedback and recovery,” in Proc. IEEE Wirel. Commun. Netw. Conf. (WCNC).   IEEE, 2019, pp. 1–5.
  17. Y. Zhang, J. Sun, G. Gui, Y. Lin, H. Gacanin, and F. Adachi, “Attention mechanism based intelligent channel feedback for mmWave massive MIMO systems,” arXiv preprint arXiv:2208.06570, 2022.
  18. B. Tolba, M. Elsabrouty, M. G. Abdu-Aguye, H. Gacanin, and H. M. Kasem, “Massive MIMO CSI feedback based on generative adversarial network,” IEEE Commun. Lett., vol. 24, no. 12, pp. 2805–2808, 2020.
  19. M. Hussien, K. K. Nguyen, and M. Cheriet, “PRVNet: A novel partially-regularized variational autoencoders for massive MIMO CSI feedback,” in 2022 IEEE Wirel. Commun. Netw. Conf. (WCNC).   IEEE, 2022, pp. 2286–2291.
  20. S. Ji and M. Li, “CLNet: Complex input lightweight neural network designed for massive MIMO CSI feedback,” IEEE Wirel. Commun. Lett., vol. 10, no. 10, pp. 2318–2322, 2021.
  21. Y. Sun, W. Xu, L. Liang, N. Wang, G. Y. Li, and X. You, “A lightweight deep network for efficient CSI feedback in massive MIMO systems,” IEEE Wirel. Commun. Lett., vol. 10, no. 8, pp. 1840–1844, 2021.
  22. X. Ma, Z. Gao, F. Gao, and M. Di Renzo, “Model-driven deep learning based channel estimation and feedback for millimeter-wave massive hybrid MIMO systems,” IEEE J. Sel. Areas Commun., vol. 39, no. 8, pp. 2388–2406, 2021.
  23. J. Guo, C.-K. Wen, S. Jin, and G. Y. Li, “Convolutional neural network-based multiple-rate compressive sensing for massive MIMO CSI feedback: Design, simulation, and analysis,” IEEE Trans. Wirel. Commun., vol. 19, no. 4, pp. 2827–2840, 2020.
  24. Y. Wang, J. Sun, J. Wang, J. Yang, T. Ohtsuki, B. Adebisi, and H. Gacanin, “Multi-rate compression for downlink CSI based on transfer learning in FDD massive MIMO systems,” in Proc. IEEE 94th Veh. Technol. Conf. (VTC2021-Fall).   IEEE, 2021, pp. 1–5.
  25. Z. Lu, J. Wang, and J. Song, “Multi-resolution CSI feedback with deep learning in massive MIMO system,” in Proc. IEEE Int. Conf. Commun. (ICC).   IEEE, 2020, pp. 1–6.
  26. S. Tang, J. Xia, L. Fan, X. Lei, W. Xu, and A. Nallanathan, “Dilated convolution based CSI feedback compression for massive MIMO systems,” IEEE Trans. Veh. Technol., vol. 71, no. 10, pp. 11 216–11 221, 2022.
  27. Z. Hu, J. Guo, G. Liu, H. Zheng, and J. Xue, “MRFNet: A deep learning-based CSI feedback approach of massive MIMO systems,” IEEE Commun. Lett., vol. 25, no. 10, pp. 3310–3314, 2021.
  28. Y. Xu, M. Zhao, S. Zhang, and H. Jin, “DFECsinet: Exploiting diverse channel features for massive MIMO CSI feedback,” in Proc. 13th Int. Conf. Wirel. Commun. Signal Process. (WCSP).   IEEE, 2021, pp. 1–5.
  29. Z. Cao, W.-T. Shih, J. Guo, C.-K. Wen, and S. Jin, “Lightweight convolutional neural networks for CSI feedback in massive MIMO,” IEEE Commun. Lett., vol. 25, no. 8, pp. 2624–2628, 2021.
  30. X. Yu, X. Li, H. Wu, and Y. Bai, “DS-NLCsinet: Exploiting non-local neural networks for massive MIMO CSI feedback,” IEEE Commun. Lett., vol. 24, no. 12, pp. 2790–2794, 2020.
  31. X. Song, J. Wang, J. Wang, G. Gui, T. Ohtsuki, H. Gacanin, and H. Sari, “SALDR: Joint self-attention learning and dense refine for massive MIMO CSI feedback with multiple compression ratio,” IEEE Wirel. Commun. Lett., vol. 10, no. 9, pp. 1899–1903, 2021.
  32. X. He, K. Zhao, and X. Chu, “AutoML: A survey of the state-of-the-art,” Knowledge-Based Syst., vol. 212, p. 106622, 2021.
  33. S. K. Karmaker, M. M. Hassan, M. J. Smith, L. Xu, C. Zhai, and K. Veeramachaneni, “AutoML to date and beyond: Challenges and opportunities,” ACM Computing Surveys (CSUR), vol. 54, no. 8, pp. 1–36, 2021.
  34. Y. Xu, L. Xie, X. Zhang, X. Chen, G.-J. Qi, Q. Tian, and H. Xiong, “PC-DARTS: partial channel connections for memory-efficient architecture search,” in Proc. 8th Int. Conf. Learn. Represent., (ICLR), 2020, pp. 26–30.
  35. 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.
  36. S. Jaeckel, L. Raschkowski, K. Börner, and L. Thiele, “QuaDRiGa: A 3-D multi-cell channel model with time evolution for enabling virtual field trials,” IEEE Trans. Antennas Propag., vol. 62, no. 6, pp. 3242–3256, 2014.
  37. J. Poutanen, K. Haneda, L. Liu, C. Oestges, F. Tufvesson, and P. Vainikainen, “Parameterization of the COST 2100 MIMO channel model in indoor scenarios,” in Proc. Eur. Conf. Antennas Propag. (EUCAP).   IEEE, 2011, pp. 3606–3610.
  38. N. Song and T. Yang, “Machine learning enhanced CSI acquisition and training strategy for FDD massive MIMO,” in 2021 IEEE Wirel. Commun. Netw. Conf. (WCNC), 2021, pp. 1–6.
  39. W. Utschick, V. Rizzello, M. Joham, Z. Ma, and L. Piazzi, “Learning the CSI recovery in FDD systems,” IEEE Trans. Wirel. Commun., vol. 21, no. 8, pp. 6495–6507, 2022.
  40. C.-K. Wen, S. Jin, K.-K. Wong, J.-C. Chen, and P. Ting, “Channel estimation for massive MIMO using gaussian-mixture bayesian learning,” IEEE Trans. Wirel. Commun., vol. 14, no. 3, pp. 1356–1368, 2014.
  41. G. Powell and I. Percival, “A spectral entropy method for distinguishing regular and irregular motion of hamiltonian systems,” J. Phys. A-Math. Gen., vol. 12, no. 11, p. 2053, 1979.
  42. S. Mourya, S. Amuru, and K. K. Kuchi, “A spatially separable attention mechanism for massive MIMO CSI feedback,” IEEE Wirel. Commun. Lett., vol. 12, no. 1, pp. 40–44, 2023.
  43. B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, “Learning transferable architectures for scalable image recognition,” in Proc. IEEE conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 8697–8710.
  44. H. Liu, K. Simonyan, and Y. Yang, “DARTS: differentiable architecture search,” in Proc. 7th Int. Conf. Learn. Represent. (ICLR), 2019, pp. 6–9.
  45. E. Real, S. Moore, A. Selle, S. Saxena, Y. L. Suematsu, J. Tan, Q. V. Le, and A. Kurakin, “Large-scale evolution of image classifiers,” in Proc. 34th Int. Conf. Machine Learning (PMLR), vol. 70.   PMLR, Aug 2017, pp. 2902–2911.
  46. A. Klein, S. Falkner, S. Bartels, P. Hennig, and F. Hutter, “Fast bayesian optimization of machine learning hyperparameters on large datasets,” in Proc. 20th Int. Conf. Artif. Intell. Stat., A. Singh and J. Zhu, Eds., vol. 54.   PMLR, 20–22 Apr 2017, pp. 528–536.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now