Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems (2312.04062v2)

Published 7 Dec 2023 in cs.IT, cs.AI, eess.SP, and math.IT

Abstract: Accurate channel state information (CSI) is essential for downlink precoding in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems with orthogonal frequency-division multiplexing (OFDM). However, obtaining CSI through feedback from the user equipment (UE) becomes challenging with the increasing scale of antennas and subcarriers and leads to extremely high CSI feedback overhead. Deep learning-based methods have emerged for compressing CSI but these methods generally require substantial collected samples and thus pose practical challenges. Moreover, existing deep learning methods also suffer from dramatically growing feedback overhead owing to their focus on full-dimensional CSI feedback. To address these issues, we propose a low-overhead Incorporation-Extrapolation based Few-Shot CSI feedback Framework (IEFSF) for massive MIMO systems. An incorporation-extrapolation scheme for eigenvector-based CSI feedback is proposed to reduce the feedback overhead. Then, to alleviate the necessity of extensive collected samples and enable few-shot CSI feedback, we further propose a knowledge-driven data augmentation (KDDA) method and an artificial intelligence-generated content (AIGC) -based data augmentation method by exploiting the domain knowledge of wireless channels and by exploiting a novel generative model, respectively. Experimental results based on the DeepMIMO dataset demonstrate that the proposed IEFSF significantly reduces CSI feedback overhead by 64 times compared with existing methods while maintaining higher feedback accuracy using only several hundred collected samples.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. E. G. Larsson, O. Edfors, F. Tufvesson, and T. L. Marzetta, “Massive MIMO for next generation wireless systems,” IEEE Commun. Mag., vol. 52, no. 2, pp. 186–195, Feb. 2014.
  2. J. Feng, S. Ma, G. Yang, and H. V. Poor, “Impact of Antenna Correlation on Full-Duplex Two-Way Massive MIMO Relaying Systems,” IEEE Trans. Wireless Commun., vol. 17, no. 6, pp. 3572–3587, Jun. 2018.
  3. J. Feng, S. Ma, S. Aïssa, and M. Xia, “Two-way massive MIMO relaying systems with non-ideal transceivers: Joint power and hardware scaling,” IEEE Trans. Commun., vol. 67, no. 12, pp. 8273–8289, Dec. 2019.
  4. W. Tan and S. Ma, “Antenna array topologies for mmWave massive MIMO systems: Spectral efficiency analysis,” IEEE Trans. Veh. Technol., vol. 71, no. 12, pp. 12 901–12 915, Dec. 2022.
  5. X. Yang, S. Ma, and S. Jin, “Antenna selection for asymmetrical uplink and downlink transceivers in massive MIMO systems,” IEEE Trans. Wireless Commun., pp. 1–1, 2023.
  6. B. Zhou, X. Yang, S. Ma, F. Gao, and G. Yang, “Pay less but get more: A dual-attention-based channel estimation network for massive MIMO systems with low-density pilots,” IEEE Trans. Wireless Commun., pp. 1–1, 2023.
  7. D. J. Love, R. W. Heath, V. K. N. 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, Oct. 2008.
  8. C.-K. Wen, W.-T. Shih, and S. Jin, “Deep learning for massive MIMO CSI feedback,” IEEE Wireless Commun. Lett., vol. 7, no. 5, pp. 748–751, Oct. 2018.
  9. 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. Wireless Commun., vol. 19, no. 4, pp. 2827–2840, Apr. 2020.
  10. X. Chen, C. Deng, B. Zhou, H. Zhang, G. Yang, and S. Ma, “High-accuracy CSI feedback with super-resolution network for massive MIMO systems,” IEEE Wireless Commun. Lett., vol. 11, no. 1, pp. 141–145, Jan. 2022.
  11. Y. Cui, A. Guo, and C. Song, “TransNet: Full attention network for CSI feedback in FDD massive MIMO system,” IEEE Wireless Commun. Lett., vol. 11, no. 5, pp. 903–907, May 2022.
  12. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Proc. NIPS, May 2017, pp. 5998–6008.
  13. J. Wang, G. Gui, T. Ohtsuki, B. Adebisi, H. Gacanin, and H. Sari, “Compressive sampled CSI feedback method based on deep learning for FDD massive MIMO systems,” IEEE Trans. Commun., vol. 69, no. 9, pp. 5873–5885, Sep. 2021.
  14. 3GPP, “NR; Physical layer procedures for data,” 3GPP, Sophia Antipolis, France, TS 38.214 V17.1.0, May 2022.
  15. M. Chen, J. Guo, C.-K. Wen, S. Jin, G. Y. Li, and A. Yang, “Deep learning-based implicit CSI feedback in massive MIMO,” IEEE Trans. Commun., vol. 70, no. 2, pp. 935–950, Feb. 2022.
  16. W. Liu, W. Tian, H. Xiao, S. Jin, X. Liu, and J. Shen, “EVCsiNet: Eigenvector-based CSI feedback under 3GPP link-level channels,” IEEE Wireless Commun. Lett., vol. 10, no. 12, pp. 2688–2692, Dec. 2021.
  17. H. Shen, L. Zhao, F. Wang, and Y. Cao, “MixerNet: Deep learning for eigenvector-based CSI feedback,” in Proc. WCSP, Nov. 2022, pp. 1167–1171.
  18. H. Xiao, Z. Wang, D. Li, W. Tian, X. Liu, W. Liu, S. Jin, J. Shen, Z. Zhang, and N. Yang, “AI enlightens wireless communication: A transformer backbone for CSI feedback,” arXiv:2206.07949, Jun. 2022.
  19. Z. Liu and Z. Ding, “Training deep learning models for massive MIMO csi feedback with small datasets in new environments,” arXiv:2211.14785, Nov. 2022.
  20. OpenAI, “Introducing ChatGPT.” [Online]. Available: https://openai.com/blog/chatgpt.
  21. A. Ramesh, P. Dhariwal, A. Nichol, C. Chu, and M. Chen, “Hierarchical text-conditional image generation with CLIP latents,” arXiv:2204.06125, Apr. 2022.
  22. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-resolution image synthesis with latent diffusion models,” in Proc. IEEE/CVF CVPR, Jun. 2022, pp. 10 674–10 685.
  23. Y. Cao, S. Li, Y. Liu, Z. Yan, Y. Dai, P. S. Yu, and L. Sun, “A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT,” arXiv:2303.04226, Mar. 2023.
  24. J. Wu, W. Gan, Z. Chen, S. Wan, and H. Lin, “AI-generated content (AIGC): A survey,” arXiv:2304.06632, Mar. 2023.
  25. A. Galashov, J. S. Merel, and N. Heess, “Data augmentation for efficient learning from parametric experts,” in Proc. NeurIPS, Dec. 2022, pp. 31 484–31 496.
  26. Y. Chen, Z. Yan, and Y. Zhu, “A unified framework for generative data augmentation: A comprehensive survey,” arXiv:2310.00277, Sep. 2023.
  27. Z. Yang, F. Zhan, K. Liu, M. Xu, and S. Lu, “AI-generated images as data source: The dawn of synthetic era,” arXiv:2310.01830, Oct. 2023.
  28. Y. Yang, Y. Li, W. Zhang, F. Qin, P. Zhu, and C.-X. Wang, “Generative-adversarial-network-based wireless channel modeling: Challenges and opportunities,” IEEE Commun. Mag., vol. 57, no. 3, pp. 22–27, Mar. 2019.
  29. 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. Wireless Commun., vol. 19, no. 5, pp. 3133–3143, Feb. 2020.
  30. H. Xiao, W. Tian, W. Liu, and J. Shen, “ChannelGAN: Deep learning-based channel modeling and generating,” IEEE Wireless Commun. Lett., vol. 11, no. 3, pp. 650–654, Mar. 2022.
  31. Y. Li, R. Zhang, J. Lu, and E. Shechtman, “Few-shot image generation with elastic weight consolidation,” in Proc. NeurIPS, Dec. 2020, pp. 15 885–15 896.
  32. T. Chen, J. Guo, S. Jin, C.-K. Wen, and G. Y. Li, “A novel quantization method for deep learning-based massive MIMO CSI feedback,” in Proc. IEEE GlobalSIP, Nov. 2019, pp. 1–5.
  33. B. Zhou, S. Ma, and G. Yang, “Transformer-based CSI feedback with hybrid learnable non-uniform quantization for massive MIMO systems,” in Proc. WOCC, May 2023, pp. 1–5.
  34. M. Wang, F. Gao, N. Shlezinger, M. F. Flanagan, and Y. C. Eldar, “A block sparsity based estimator for mmWave massive MIMO channels with beam squint,” IEEE Trans. Signal Process., vol. 68, pp. 49–64, Jan. 2020.
  35. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE/CVF CVPR, Jun. 2016, pp. 770–778.
  36. J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer normalization,” arXiv:1607.06450, Jul. 2016.
  37. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. ICLR, May 2015. [Online]. Available: http://arxiv.org/abs/1412.6980.
  38. T. R. Shaham, T. Dekel, and T. Michaeli, “Singan: Learning a generative model from a single natural image,” in Proc. IEEE/CVF CVPR, 2019, pp. 4570–4580.
  39. S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proc. ICML, Jul. 2015, pp. 448–456.
  40. T. Miyato, T. Kataoka, M. Koyama, and Y. Yoshida, “Spectral normalization for generative adversarial networks,” in Proc. ICLR, Apr. 2018. [Online]. Available: https://openreview.net/forum?id=B1QRgziT-.
  41. M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” arXiv:1701.07875, Dec. 2017.
  42. I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved training of Wasserstein GANs,” in Proc. NIPS, Dec. 2017, pp. 5767–5777.
  43. A. Alkhateeb, “DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications,” arXiv:1902.06435, Feb. 2019.
  44. Remcom, “Wireless Insite.” [Online]. Available: http://www.remcom.com/wireless-insite.
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
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets