Rateless DeepJSCC for Broadcast Channels: a Rate-Distortion-Complexity Tradeoff

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.

Figures (5)

• Figure 1: Schematic diagram for nonlinear transform rateless source-channel coding. At the transmitter, the analysis transform $g_a$ extracts semantic information ${\bf{y}}$ from source image, the analysis transform $h_a$ produces auxiliary variable $\bf{z}$, the synthesis transforms $h_s$ and $h_c$ predict bit likelihoods ${\bm{\mu}}$ and LT parameters ${\bm{\rho}}$, ${\bm{\Omega}}$ to generate rateless symbols $\bf{v}$. At the receiver, the synthesis transforms $h_s$ and $h_c$ predict bit likelihoods and LT parameters, the scaling function $f_s$ estimates the number of received symbols $\bf{n}$ and decoding iterations $\bm{\eta}$ to perform BP decoding on demodulator soft values ${\bf{\hat{v}}}$, the synthesis transform ${g_s}$ takes soft decoder outputs $\mathcal{M}$ and recovers image information.
• Figure 2: The LT encoding and decoding process in NTRSCC. Consider the j-th feature channel. The extracted latent features ${\bf{y}}_j$ are quantized to obtain bitstream ${\bf{b}}_j$. ${\bf{y}}_j$ also produces dimension-wise prior ${\bm{\mu}}_j$, which guides the prediction of degree distributions ${\bm{\Omega }}_j$ and ${\bm{\rho}}_j$. While the rateless symbols are produced indefinitely, the encoder employs a polling strategy based on the sum log-probability of each feature channel to generate channel symbols ${\bf{v}}_j$. The decoder stops receiving more rateless channel symbols when the total number of collected symbols reaches $\bf{n}$. The BP decoder processes demodulated LLR ${\bf{\hat{v}}}_j$ and the prior LLR ${\bm{\mu}}_j$, until the number of iterations reach ${\left\lceil \eta \right\rceil }$, and the final outputs are the soft likelihoods $\mathcal{M}_j$.
• Figure 3: Rate-distortion tradeoff comparisons.
• Figure 4: Complexity-distortion tradeoff comparisons.
• Figure 5: broadcasting efficiency comparisons

Theorems & Definitions (11)

• Remark 1
• Theorem 1
• proof
• Remark 2
• Theorem 2
• proof
• Remark 3
• Theorem 3
• proof
• Remark 4