Channel-Aware Preemptive Scheduling for Semantic Communication with Truncated Diffusion and Path Compensation

TL;DR

This paper introduces CAPS-TDPC, a channel-aware scheduling framework for semantic communication that reduces latency by enabling early transmission of diffusion model outputs under good channel conditions, with path compensation to preserve semantic quality.

Contribution

It proposes a novel preemptive scheduling method that interrupts diffusion processes for transmission based on channel state, along with a receiver-side compensation mechanism to maintain semantic fidelity.

Findings

Significantly reduces end-to-end latency in semantic communication.

Maintains high-fidelity semantic reconstruction despite early transmission.

Enhances robustness in fast fading wireless environments.

Abstract

Semantic communication (SemCom) presents a transformative paradigm for alleviating bandwidth limitations in mobile networks by transmitting task-relevant semantic features instead of raw data bits. While SemCom systems utilizing diffusion models achieve superior generation quality, existing research treats semantic generation and wireless transmission as temporally independent processes. This separation neglects the intrinsic conflict between the multi-step iterative delays inherent in diffusion models and the time-varying fading characteristics of wireless channels. To address this discrepancy, this paper proposes a channel-aware preemptive scheduling with truncated diffusion and path compensation (CAPS-TDPC) framework. Contrary to conventional methods that require completion of the generation phase prior to transmission, the proposed framework implements a channel-driven scheduling mechanism: each user maintains a countdown inversely proportional to its instantaneous channel gain, and the user with the shortest countdown transmits immediately, regardless of whether its diffusion process has completed. This design permits the interruption of the forward diffusion process to enable early transmission under favorable channel conditions. In addition, a receiver-side compensation mechanism grounded in path dynamics is developed to mitigate the semantic loss resulting from such interruptions. A path deficit metric is proposed at the receiver to quantify the recovery difficulty of distinct image blocks by incorporating the velocity field of the inverse dynamics model, which allows for adaptive weighted inverse sampling. Experimental evaluations demonstrate that the proposed framework substantially reduces the end-to-end latency while maintaining the high-fidelity semantic reconstruction, thereby enhancing the system robustness in fast fading channel environments.