Deep Variable-Length Feedback Codes

2026-02-08

AI Summary

This work proposes DeepVLF, a novel deep learning framework for variable-length feedback channel coding that overcomes limitations of existing methods—such as fixed blocklengths, performance degradation at high code rates, and lack of adaptivity. DeepVLF introduces two architectures: receiver-driven (DeepVLF-R) and transmitter-driven (DeepVLF-T), integrating bit grouping, Transformer-based encoders and decoders, and a dynamic termination mechanism. Operating over both AWGN and 5G-NR fading channels, the framework autonomously learns a two-stage strategy resembling the Schalkwijk–Kailath scheme, offering both interpretability and alignment with information-theoretic principles. Experimental results demonstrate that DeepVLF reduces channel uses by 20%–55% at the same block error rate compared to state-of-the-art approaches, while effectively mitigating the error floor in high-rate regimes.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Learning & Optimization for NLP
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Deep learning has enabled significant advances in feedback-based channel coding, yet existing learned schemes remain fundamentally limited: they employ fixed block lengths, suffer degraded performance at high rates, and cannot fully exploit the adaptive potential of feedback. This paper introduces Deep Variable-Length Feedback (DeepVLF) coding, a flexible coding framework that dynamically adjusts transmission length via learned feedback. We propose two complementary architectures: DeepVLF-R, where termination is receiver-driven, and DeepVLF-T, where the transmitter controls termination. Both architectures leverage bit-group partitioning and transformer-based encoder-decoder networks to enable fine-grained rate adaptation in response to feedback. Evaluations over AWGN and 5G-NR fading channels demonstrate that DeepVLF substantially outperforms state-of-the-art learned feedback codes. It achieves the same block error rate with 20%-55% fewer channel uses and lowers error floors by orders of magnitude, particularly in high-rate regimes. Encoding dynamics analysis further reveals that the models autonomously learn a two-phase strategy analogous to classical Schalkwijk-Kailath coding: an initial information-carrying phase followed by a noise-cancellation refinement phase. This emergent behavior underscores the interpretability and information-theoretic alignment of the learned codes.

Problem

• feedback coding
• variable-length coding
• deep learning
• channel coding
• rate adaptation

Innovation

• DeepVLF
• variable-length feedback coding
• transformer-based encoder-decoder
• rate adaptation
• learned channel coding