Transferable Deployment of Semantic Edge Inference Systems via Unsupervised Domain Adaption

--This paper investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data into semantic features and then transmit them to an edge server for subsequent data fusion and task inference. The inference accuracy is determined by efficient training of the feature encoder/decoder using labeled data samples. Due to the difference in sensing data and communication channel distributions, deploying the system in a new environment may induce high costs in annotating data labels and re-training the encoder/decoder models. T o achieve cost-effective transferable system deployment, we propose an efficient Domain Adaptation method for Semantic Edge INference systems (DASEIN) that can maintain high inference accuracy in a new environment without the need for labeled samples. Specifically, DASEIN exploits the task-relevant data correlation between different deployment scenarios by leveraging the techniques of unsupervised domain adaptation and knowledge distillation. It devises an efficient two-step adaptation procedure that sequentially aligns the data distributions and adapts to the channel variations. Numerical results show that, under a substantial change in sensing data distributions, the proposed DASEIN outperforms the best-performing benchmark method by 7.09 % and 21.33 % in inference accuracy when the new environment has similar or 25 dB lower channel signal to noise power ratios (SNRs), respectively. This verifies the effectiveness of the proposed method in adapting both data and channel distributions in practical transfer deployment applications. Index T erms --Semantic communications, edge inference, transfer learning, unsupervised domain adaptation. Hanks to the advancement of artificial intelligence (AI), it becomes prevalent in recent years to deploy smart Internet of Things (IoT) systems using deep neural networks (DNNs) to perform complex inference tasks, e.g., computer vision based object recognition [1]-[3]. In particular, wireless IoT devices, such as video surveillance cameras, are systematically deployed at target locations to collect real-time sensing data and collaboratively accomplish specific inference tasks. The performance of on-device AI inference, however, is significantly constrained by the limited battery energy and computing power of IoT devices.