Rateless DeepJSCC for Broadcast Channels: a Rate-Distortion-Complexity Tradeoff
🤖 AI Summary
This work addresses the challenge in wireless edge data-intensive broadcasting where existing deep joint source-channel coding schemes struggle to balance distortion, rate, and decoding complexity while failing to accommodate heterogeneous receiver requirements. To this end, the paper proposes a Nonlinear Transform Rateless Source-Channel Coding (NTRSCCC) framework that, for the first time, integrates learnable nonlinear source transformations with physical-layer Luby Transform (LT) codes, enabling variable-length transmission. The framework further incorporates an unequal error protection mechanism guided by receiver-side information. Through end-to-end optimization of rateless parameters and approximate gradient backpropagation, NTRSCC achieves a controllable trade-off among distortion, rate, and complexity. Experimental results demonstrate that under stringent resource constraints, NTRSCC significantly improves image broadcast quality across heterogeneous multi-user edge devices.
Application Category
📝 Abstract
In recent years, numerous data-intensive broadcasting applications have emerged at the wireless edge, calling for a flexible tradeoff between distortion, transmission rate, and processing complexity. While deep learning-based joint source-channel coding (DeepJSCC) has been identified as a potential solution to data-intensive communications, most of these schemes are confined to worst-case solutions, lack adaptive complexity, and are inefficient in broadcast settings. To overcome these limitations, this paper introduces nonlinear transform rateless source-channel coding (NTRSCC), a variable-length JSCC framework for broadcast channels based on rateless codes. In particular, we integrate learned source transformations with physical-layer LT codes, develop unequal protection schemes that exploit decoder side information, and devise approximations to enable end-to-end optimization of rateless parameters. Our framework enables heterogeneous receivers to adaptively adjust their received number of rateless symbols and decoding iterations in belief propagation, thereby achieving a controllable tradeoff between distortion, rate, and decoding complexity. Simulation results demonstrate that the proposed method enhances image broadcast quality under stringent communication and processing budgets over heterogeneous edge devices.
Problem
Research questions and friction points this paper is trying to address.
Rateless coding
Joint source-channel coding
Broadcast channels
Rate-distortion-complexity tradeoff
Deep learning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Rateless coding
DeepJSCC
Broadcast channels
Unequal error protection
End-to-end optimization
🔎 Similar Papers
No similar papers found.
