Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes
This work addresses a domain-specific problem in coding theory for communication scenarios lacking high-performing structured codes, representing an incremental advance by extending existing methods to active feedback.
The paper tackled the challenge of designing practical codes for communication channels with active feedback, a long-standing open problem in coding theory, by implementing transformer architectures at both transmitter and receiver that interact sequentially, achieving new state-of-the-art block error rate performance, particularly at low SNR.
Deep neural network (DNN)-assisted channel coding designs, such as low-complexity neural decoders for existing codes, or end-to-end neural-network-based auto-encoder designs are gaining interest recently due to their improved performance and flexibility; particularly for communication scenarios in which high-performing structured code designs do not exist. Communication in the presence of feedback is one such communication scenario, and practical code design for feedback channels has remained an open challenge in coding theory for many decades. Recently, DNN-based designs have shown impressive results in exploiting feedback. In particular, generalized block attention feedback (GBAF) codes, which utilizes the popular transformer architecture, achieved significant improvement in terms of the block error rate (BLER) performance. However, previous works have focused mainly on passive feedback, where the transmitter observes a noisy version of the signal at the receiver. In this work, we show that GBAF codes can also be used for channels with active feedback. We implement a pair of transformer architectures, at the transmitter and the receiver, which interact with each other sequentially, and achieve a new state-of-the-art BLER performance, especially in the low SNR regime.