# All you need is feedback: Communication with block attention feedback codes

arXiv: https://arxiv.org/abs/2206.09457 · HTML: https://mlsanity.com/paper/2206.09457/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 19 Jun 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [A Survey of Transformers](https://mlsanity.com/paper/2106.04554/) (2021)
- [Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1402.1128/) (2014)
- [Deepcode: Feedback Codes via Deep Learning](https://mlsanity.com/paper/1807.00801/) (2018)
- [Transformer-Empowered 6G Intelligent Networks: From Massive MIMO Processing to Semantic Communication](https://mlsanity.com/paper/2205.03770/) (2022)
- [Deep Extended Feedback Codes](https://mlsanity.com/paper/2105.01365/) (2021)
- [AttentionCode: Ultra-Reliable Feedback Codes for Short-Packet Communications](https://mlsanity.com/paper/2205.14955/) (2022)
- [DRF Codes: Deep SNR-Robust Feedback Codes](https://mlsanity.com/paper/2112.11789/) (2021)
- [Sporadic Ultra-Time-Critical Crowd Messaging in V2X](https://mlsanity.com/paper/2003.01906/) (2020)

## Built on by (most cited first, 10 of 10)

- [Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes](https://mlsanity.com/paper/2211.01730/) (2022)
- [Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning](https://mlsanity.com/paper/2304.13178/) (2023)
- [LightCode: Light Analytical and Neural Codes for Channels with Feedback](https://mlsanity.com/paper/2403.10751/) (2024)
- [DEEP-IoT: Downlink-Enhanced Efficient-Power Internet of Things](https://mlsanity.com/paper/2403.00321/) (2024)
- [Coding for Gaussian Two-Way Channels: Linear and Learning-Based Approaches](https://mlsanity.com/paper/2401.00477/) (2023)
- [DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning](https://mlsanity.com/paper/2402.08864/) (2024)
- [Interpreting Training Aspects of Deep-Learned Error-Correcting Codes](https://mlsanity.com/paper/2305.04347/) (2023)
- [Deep Variable-Length Feedback Codes](https://mlsanity.com/paper/2602.07881/) (2026)
- [Rich-ARQ: From 1-bit Acknowledgment to Rich Neural Coded Feedback](https://mlsanity.com/paper/2602.07886/) (2026)
- [MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes](https://mlsanity.com/paper/2609.00715/) (2026)

## Abstract (arXiv)

Deep learning based channel code designs have recently gained interest as an alternative to conventional coding algorithms, particularly for channels for which existing codes do not provide effective solutions. Communication over a feedback channel is one such problem, for which promising results have recently been obtained by employing various deep learning architectures. In this paper, we introduce a novel learning-aided code design for feedback channels, called generalized block attention feedback (GBAF) codes, which i) employs a modular architecture that can be implemented using different neural network architectures; ii) provides order-of-magnitude improvements in the probability of error compared to existing designs; and iii) can transmit at desired code rates.