Task-Oriented Communication with Hybrid-Precision Models
Distributed, Parallel, and Cluster Computing
Summary
The authors propose a new way to run AI tasks partly on small edge devices and partly on servers to reduce delays and resource use. They split the AI model so the edge device handles simple, binary data, which is sent efficiently to the server that completes the task with full data precision. To keep everything working smoothly, they created special methods for processing, sending, and training the model. Their tests on a big image dataset show this hybrid approach balances communication speed, device workload, and accuracy better than previous methods.
Authors
Songjie Xie, Wei Guo, Shenghui Song, Jun Zhang, Ying-Jun Angela Zhang, Khaled B. Letaief
Abstract
Edge inference has emerged as a promising solution for the proliferation of artificial intelligence (AI) services by deploying models at the network edge to circumvent cloud-routing latency. Existing edge inference approaches mainly focused on either cooperative inference to reduce latency or lightweight model design to fit resource-constrained devices. These solutions often address the communication and computation challenges separately, and thus struggle to achieve a balanced trade-off among transmission efficiency, on-device processing cost, and inference accuracy. To bridge this gap, this paper proposes a hybrid-precision task-oriented communication framework for edge inference to holistically balance communication, on-device computation, and utility. In this framework, a binarized front-end is deployed on the edge device to extract and transmit binary features via orthogonal frequency-division multiplexing (OFDM) signals, while a full-precision back-end on the edge server performs the final inference. To ensure model consistency, we introduce an on-device binarization method tailored for split inference and develop an integrated channel-aware transmission scheme featuring subcarrier-based feature calibration. Furthermore, a knowledge distillation (KD)-based training strategy, supported by specialized gradient estimators, is developed to optimize the end-to-end system and inherit semantic knowledge from a full-precision teacher model. Extensive experiments on the large-scale ImageNet dataset demonstrate the superiority of the proposed hybrid system. Our analysis confirms that this design achieves an optimal trade-off among communication efficiency, on-device computational cost, and inference accuracy, outperforming existing edge inference solutions.