AttentionCode: Ultra-Reliable Feedback Codes for Short-Packet Communications

Shao, Yulin; Ozfatura, Emre; Perotti, Alberto; Popović, Branislav M.; Gündüz, Deniz

doi:10.1109/tcomm.2023.3280563

Cited by 3 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decoder uses a bidirectional LSTM architecture along with an SNR-aware attention [25,26,27,28,29] network to decode the message. In comparison with the transformer-based codes [18,19], the LSTM-based DRF and DEF codes achieve lower BLER for lower feedback channel SNR ranges (i.e., feedback SNR 0-10 dB). LSTM-based designs also require less computational complexity for the same block length in comparison with their transformer-based counterparts [18].…”

Section: Introductionmentioning

confidence: 95%

“…In comparison with the transformer-based codes [18,19], the LSTM-based DRF and DEF codes achieve lower BLER for lower feedback channel SNR ranges (i.e., feedback SNR 0-10 dB). LSTM-based designs also require less computational complexity for the same block length in comparison with their transformer-based counterparts [18]. The major contributions of this paper can be summarized as follows:…”

Section: Introductionmentioning

confidence: 95%

“…More recently, some progress has been made by applying Machine Learning (ML) techniques, where channel decoding is regarded as a classi ication task, and the encoder and decoder, implemented as Deep Neural Network (DNN) architectures, are jointly trained in a data-driven fashion [15,16,17,18,19,20,21]. In this context, the encoder/decoder pair forms an over-complete autoencoder, where the encoder DNN adds redundancy to the latent representation of the message to cope with the channel noise, and the decoder DNN extracts features from the noisy received signal for ef icient classi ication.…”

Section: Abstract -Attention Neural Network Channel Coding Communicat...mentioning

confidence: 99%

“…After the initial introduction of the DRF codes [22], other codes with more complex DNN architectures were proposed for the feedback channel. In particular, in [18] the authors proposed AttentionCode based on self-attention and restructuring, for reliable short-packet communications. In [19], the Generalized Block Attention Feedback (GBAF) codes were proposed based on the transformer architecture.…”

Section: Introductionmentioning

confidence: 99%

“…In [20], the authors extend GBAF codes to the active coded feedback scenario by implementing a pair of transformer architectures, at the transmitter and the receiver, which interact with each other sequentially. The transformer-based designs AttentionCode and GBAF [18,19] outperform RNN and Long Short Term Memory (LSTM)-based codes [15,17] in terms of the Block Error Rate (BLER) for channels with noiseless feedback or when the feedback Signal to Noise Ratio (SNR) is high, typically 20 dB and above. Despite their signi icant performance, DNN-based codes are very sensitive to the mismatch between the actual channel SNR and the SNR that the NN has been trained for, which limits their application in practical communication systems with time-varying SNR values.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

DRF codes: Deep SNR-robust feedback codes

Mahdi Boloursaz Mashhadi,

Deniz Gunduz,

Alberto Perotti

et al. 2023

ITU J-FET

View full text Add to dashboard Cite

We present a new Deep Neural Network (DNN)-based error correction code for fading channels with output feedback, called the Deep SNR-Robust Feedback (DRF) code. At the encoder, parity symbols are generated by a Long Short Term Memory (LSTM) network based on the message, as well as the past forward channel outputs observed by the transmitter in a noisy fashion. The decoder uses a bidirectional LSTM architecture along with a Signal to Noise Ratio (SNR)-aware attention NN to decode the message. The proposed code overcomes two major shortcomings of DNN-based codes over channels with passive output feedback: (i) the SNR-aware attention mechanism at the decoder enables reliable application of the same trained NN over a wide range of SNR values; (ii) curriculum training with batch size scheduling is used to speed up and stabilize training while improving the SNR-robustness of the resulting code. We show that the DRF codes outperform the existing DNN-based codes in terms of both the SNR-robustness and the error rate in an Additive White Gaussian Noise (AWGN) channel with noisy output feedback. In fading channels with perfect phase compensation at the receiver, DRF codes learn to efficiently exploit knowledge of the instantaneous fading amplitude (which is available to the encoder through feedback) to reduce the overhead and complexity associated with channel estimation at the decoder. Finally, we show the effectiveness of DRF codes in multicast channels with feedback, where linear feedback codes are known to be strictly suboptimal. These results show the feasibility of automatic design of new channel codes using DNN-based language models.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 95%

Section: Abstract -Attention Neural Network Channel Coding Communicat...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

DRF codes: Deep SNR-robust feedback codes

Mahdi Boloursaz Mashhadi,

Deniz Gunduz,

Alberto Perotti

et al. 2023

ITU J-FET

View full text Add to dashboard Cite

show abstract

Is the Envelope Beneficial to Non-Orthogonal Multiple Access?

Xie,

Yi,

et al. 2024

IEEE Trans. Commun.

View full text Add to dashboard Cite

Non-orthogonal multiple access (NOMA) is capable of serving different numbers of users in the same time-frequency resource element, and this feature can be leveraged to carry additional information. In the orthogonal frequency division multiplexing (OFDM) system, a novel enhanced NOMA scheme called NOMA with informative envelope (NOMA-IE) is proposed to explore extra flexibility from the envelope of NOMA signals.In this scheme, data bits are conveyed by the quantified signal envelope in addition to classic signal constellations. The subcarrier activation patterns of different users are jointly decided by the envelope former at the transmitter of NOMA-IE. At the receiver, successive interference cancellation (SIC) is employed, and the envelope detection coefficient is introduced to eliminate the error floor. Theoretical expressions of spectral efficiency, energy efficiency, and detection complexity are provided first. Then, considering the binary phase shift keying modulation, the block error rate and bit error rate are derived based on the two-subcarrier element. The analytical results reveal that the SIC error and the index error are the main factors degrading the error performance. The numerical results demonstrate the superiority of the NOMA-IE over the OFDM and OFDM-NOMA in terms of the error rate performance when all the schemes have the same spectral efficiency and energy efficiency.

show abstract