ParaJSCC: A Parameterized Framework for Reusable Multimodal Joint Source-Channel Coding

2026-08-15

AI Summary

This study addresses encoding redundancy and inefficiency in repeated multimodal content access by proposing a parameterized framework for reusable representation services with a progressive shared-private mechanism. By converting data offline into compact parameter packages stored at edge nodes, the approach enables on-demand subset transmission and lightweight decoding to support modality selection and scalable reconstruction. Experimental results demonstrate that this method maintains reconstruction quality over noisy channels while reducing online latency by approximately 75% and decreasing selective request transmission rates by 47.8%–51.2%. These findings indicate significant improvements in edge-based multimodal service efficiency, validating the effectiveness of parameterized representations for optimizing bandwidth-constrained environments with frequent content reuse demands.

Abstract

Multimodal signals, such as visual, audio, and tactile data, are increasingly maintained as persistent digital assets in immersive communication systems and digital twins. In these settings, the same multimodal content is repeatedly accessed by heterogeneous receivers with varying modality and bandwidth requirements. Existing compression and Joint Source-Channel Coding (JSCC) methods typically follow a per-request encoding paradigm, resulting in redundant computation and low efficiency during repeated access. To address this issue, we propose ParaJSCC, a multimodal JSCC framework designed for reusable representation serving. ParaJSCC converts each multimodal sample offline at the cloud/content server into a compact, quantized parameter package, which is then stored at the edge serving node for low-latency access. During serving, only the subset required by the current request is transmitted over the wireless channel, followed by lightweight decoding at the receiver. The framework employs a progressive shared-private parameterization to support modality-selective transmission and scalable reconstruction under varying bandwidth constraints. Experiments on multimodal datasets show that ParaJSCC significantly reduces online latency (e.g., from 17.18~ms to 4.34~ms for image-only requests and from 43.96~ms to 11.21~ms for full multimodal requests) and transmission rate (by 47.8\%--51.2\% for selective requests), while maintaining strong reconstruction quality under noisy channels.

Problem

• Multimodal Joint Source-Channel Coding
• Reusable Representation
• Immersive Communication
• Encoding Efficiency

Innovation

• Parameterized JSCC
• Reusable Representation
• Progressive Shared-Private Parameterization
• Modality-Selective Transmission
• Edge Serving