Adaptive Semantic Token Communication for Transformer-based Edge Inference

TL;DR

This paper introduces an adaptive semantic communication framework using transformer-based joint source channel coding for edge inference, enabling efficient, task-aware data transmission under varying network conditions.

Contribution

It proposes a novel adaptive token selection and compression method combined with resource allocation for semantic communication in edge inference scenarios.

Findings

Outperforms existing baselines in efficiency and robustness

Effectively balances compression and task accuracy under dynamic conditions

Demonstrates potential for AI-native semantic communication in edge devices

Abstract

This paper presents an adaptive framework for edge inference based on a dynamically configurable transformer-powered deep joint source channel coding (DJSCC) architecture. Motivated by a practical scenario where a resource constrained edge device engages in goal oriented semantic communication, such as selectively transmitting essential features for object detection to an edge server, our approach enables efficient task aware data transmission under varying bandwidth and channel conditions. To achieve this, input data is tokenized into compact high level semantic representations, refined by a transformer, and transmitted over noisy wireless channels. As part of the DJSCC pipeline, we employ a semantic token selection mechanism that adaptively compresses informative features into a user specified number of tokens per sample. These tokens are then further compressed through the JSCC module, enabling a flexible token communication strategy that adjusts both the number of transmitted tokens and their embedding dimensions. We incorporate a resource allocation algorithm based on Lyapunov stochastic optimization to enhance robustness under dynamic network conditions, effectively balancing compression efficiency and task performance. Experimental results demonstrate that our system consistently outperforms existing baselines, highlighting its potential as a strong foundation for AI native semantic communication in edge intelligence applications.