International Journal of Computer Network and Information Security (IJCNIS)
IJCNIS Vol. 18, No. 1, 8 Feb. 2026
Cover page and Table of Contents: PDF (size: 1064KB)
Meta-Learning Enhanced BiLSTM Autoencoder with Channel-adaptive Quantization for Robust One-Bit Error Correction Coding
PDF (1064KB), PP.142-158
Views: 0 Downloads: 0
Author(s)
Avinash Ratre
1,*
Index Terms
Quantization, Error Correction Coding, Autoencoder, BiLSTM, Meta-Learning
Abstract
We propose a meta-learning-enhanced BiLSTM autoencoder architecture for robust one-bit error correction coding, designed to dynamically adapt to diverse channel conditions without requiring explicit retraining. The proposed method fuses a channel-aware meta-discriminator into an adversarial training framework, allowing the system to generalize across Rician, Rayleigh, and AWGN channels by adapting its decision boundaries based on temporal signal statistics. The meta-discriminator, realized as a lightweight Transformer-encoder with cross-attention, computes channel-specific embeddings from the received signal, which modulate the adversarial loss and guide the reconstruction process. Furthermore, the BiLSTM encoder-decoder utilizes bidirectional layers with residual connections to capture long-range dependencies, while a learnable one-bit quantizer with adaptive thresholds ensures efficient signal representation. The training objective combines reconstruction loss, adversarial loss, and a meta-regularization term, which stabilizes updates and refines adaptation. The meta-discriminator performs real-time parameter adjustments using a single gradient step during inference to make the system resilient to unseen channel impairments. The experiments demonstrate significant improvements in BER and MSE across various fading channels and data sizes. The Rician channel exhibits the lowest values of BER and MSE of 0.032 and 0.031, respectively, when considering a data size of 2500 symbols. The proposed work shows its dual capability to learn error-correcting codes through BiLSTMs, apart from exploiting meta-learning for channel adaptation.
Cite This Paper
Avinash Ratre, "Meta-Learning Enhanced BiLSTM Autoencoder with Channel-adaptive Quantization for Robust One-Bit Error Correction Coding", International Journal of Computer Network and Information Security(IJCNIS), Vol.18, No.1, pp.142-158, 2026. DOI:10.5815/ijcnis.2026.01.10
Reference
[1]E. Balevi and J. G. Andrews, “Autoencoder-Based Error Correction Coding for One-Bit Quantization,” IEEE Transactions on Communications, vol. 68, no. 6, pp. 3440–3451, Jun. 2020, doi: 10.1109/TCOMM.2020.2977280.
[2]M. Yang, C. Bian, and H. S. Kim, “OFDM-Guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels,” IEEE Trans Cogn Commun Netw, vol. 8, no. 2, pp. 584–599, Jun. 2022, doi: 10.1109/TCCN.2022.3151935.
[3]Z. Fan, W. Li, and K. C. Chang, “A Bidirectional Long Short-Term Memory Autoencoder Transformer for Remaining Useful Life Estimation,” Mathematics, vol. 11, no. 24, Dec. 2023, doi: 10.3390/math11244972.
[4]T. Gruber, S. Cammerer, J. Hoydis, and S. Ten Brink, “On deep learning-based channel decoding,” in 2017 51st Annual Conference on Information Sciences and Systems, CISS 2017, Institute of Electrical and Electronics Engineers Inc., May 2017. doi: 10.1109/CISS.2017.7926071.
[5]M. Ramkumar, R. Sarath Kumar, A. Manjunathan, M. Mathankumar, and J. Pauliah, “Auto-encoder and bidirectional long short-term memory based automated arrhythmia classification for ECG signal,” Biomed Signal Process Control, vol. 77, Aug. 2022, doi: 10.1016/j.bspc.2022.103826.
[6]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 GlobalSIP 2019 - 7th IEEE Global Conference on Signal and Information Processing, Proceedings, Institute of Electrical and Electronics Engineers Inc., Nov. 2019. doi: 10.1109/GlobalSIP45357.2019.8969557.
[7]T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey, “Meta-Learning in Neural Networks: A Survey,” IEEE Trans Pattern Anal Mach Intell, vol. 44, no. 9, pp. 5149–5169, Sep. 2022, doi: 10.1109/TPAMI.2021.3079209.
[8]B. Ji, M. Liu, S. Mumtazi, H. Fan, and S. Guo, “Optimization of Meta-learning Algorithms Based on Adversarial Training in Vehicular and Mobile Communications,” IEEE Trans Veh Technol, 2025, doi: 10.1109/TVT.2025.3573915.
[9]M. Moradi, “On Sequential Decoding Metric Function of Polarization-Adjusted Convolutional (PAC) Codes,” IEEE Transactions on Communications, vol. 69, no. 12, pp. 7913–7922, Dec. 2021, doi: 10.1109/TCOMM.2021.3111018.
[10]H. Ye, G. Y. Li, and B. H. Juang, “Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems,” IEEE Wireless Communications Letters, vol. 7, no. 1, pp. 114–117, Feb. 2018, doi: 10.1109/LWC.2017.2757490.
[11]Y. Guo, “A Survey on Methods and Theories of Quantized Neural Networks,” pp. 1–17, Dec. 2018, [Online]. Available: http://arxiv.org/abs/1808.04752
[12]M. Yan, Y. Yang, and S. Osher, “Robust 1-bit compressive sensing using adaptive outlier pursuit,” IEEE Transactions on Signal Processing, vol. 60, no. 7, pp. 3868–3875, Jul. 2012, doi: 10.1109/TSP.2012.2193397.
[13]J. Kosaian, K. V. Rashmi, and S. Venkataraman, “Learning a Code: Machine Learning for Approximate Non-Linear Coded Computation,” Jun. 2018, [Online]. Available: http://arxiv.org/abs/1806.01259
[14]N. Živić and O. Ur Rehman, “On using the message digest for error correction in wireless communication networks,” in IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC, 2010, pp. 491–495. doi: 10.1109/PIMRCW.2010.5670523.
[15]O. Elijah, S. K. Abdul Rahim, W. K. New, C. Y. Leow, K. Cumanan, and T. Kim Geok, “Intelligent Massive MIMO Systems for beyond 5G Networks: An Overview and Future Trends,” IEEE Access, vol. 10, pp. 102532–102563, 2022, doi: 10.1109/ACCESS.2022.3208284.
[16]C. Zou, F. Yang, J. Song, and Z. Han, “Underwater Wireless Optical Communication With One-Bit Quantization: A Hybrid Autoencoder and Generative Adversarial Network Approach,” IEEE Trans Wirel Commun, vol. 22, no. 10, pp. 6432–6444, Oct. 2023, doi: 10.1109/TWC.2023.3243212.
[17]T. Matsumine and H. Ochiai, “Recent Advances in Deep Learning for Channel Coding: A Survey,” IEEE Open Journal of the Communications Society, vol. 5, pp. 6443–6481, 2024, doi: 10.1109/OJCOMS.2024.3472094.
[18]Z. Moubarak, F. Monteiro, L. Aarif, A. Dandache, and M. Tabaa, “AI Filtering System for Optimizing Wavelet-Based Industrial Communications,” in Journal of Physics: Conference Series, Institute of Physics, 2025. doi: 10.1088/1742-6596/3028/1/012042.
[19]J. Casebeer, N. J. Bryan, and P. Smaragdis, “Meta-AF: Meta-Learning for Adaptive Filters,” IEEE/ACM Trans Audio Speech Lang Process, vol. 31, pp. 355–370, 2023, doi: 10.1109/TASLP.2022.3224288.
[20]P. Guo et al., “Few-Shot Source Separation for IoT Anti-Jamming via Multitask Learning and Meta-Learning,” IEEE Internet Things J, vol. 12, no. 11, pp. 16761–16776, 2025, doi: 10.1109/JIOT.2025.3534578.
[21]L. Li, L. Zhu, and W. Li, “HiSatFL: A Hierarchical Federated Learning Framework for Satellite Networks with Cross-Domain Privacy Adaptation,” Electronics (Switzerland), vol. 14, no. 16, Aug. 2025, doi: 10.3390/electronics14163237.
[22]R. Yang, D. Liu, D. Li, and Z. Liu, “Federated Meta-Learning based End-to-End Communication Against Channel-Aware Adversaries,” in IEEE Vehicular Technology Conference, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/VTC2024-Fall63153.2024.10757857.
[23]C. M. Zierhofer, “Adaptive Sigma-Delta Modulation With One-Bit Quantization,” 2000.
[24]Y. Plan and R. Vershynin, “One-bit compressed sensing by linear programming,” Commun Pure Appl Math, vol. 66, no. 8, pp. 1275–1297, Aug. 2013, doi: 10.1002/cpa.21442.
[25]S. Zheng, Y. Dong, and X. Chen, “Deep Reinforcement Learning-based Quantization for Federated Learning,” in IEEE Wireless Communications and Networking Conference, WCNC, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/WCNC55385.2023.10118781.
[26]C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” in Proceedings of the 34 th International Conference on Machine Learning, 2017, pp. 1126–1135. doi: 10.5555/3305381.3305498.
[27]P. Cheng, C. Liu, C. Li, D. Shen, R. Henao, and L. Carin, “Straight-Through Estimator as Projected Wasserstein Gradient Flow,” in Third workshop on Bayesian Deep Learning (NeurIPS 2018), Montréal, Canada., Oct. 2019, pp. 1–9. [Online]. Available: http://arxiv.org/abs/1910.02176
[28]J. Xia and D. Gunduz, “Meta-learning Based Beamforming Design for MISO Downlink,” in IEEE International Symposium on Information Theory - Proceedings, Institute of Electrical and Electronics Engineers Inc., Jul. 2021, pp. 2954–2959. doi: 10.1109/ISIT45174.2021.9518251.
[29]E. Balevi and J. G. Andrews, “High Rate Communication over One-Bit Quantized Channels via Deep Learning and LDPC Codes,” in IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC, Institute of Electrical and Electronics Engineers Inc., May 2020. doi: 10.1109/SPAWC48557.2020.9154208.
[30]J. Li, M. Khodak, S. Caldas, and A. Talwalkar, “Differentially Private Meta-Learning,” in 8th International Conference on Learning Representations, ICLR 2020, International Conference on Learning Representations, ICLR, 2020.