Task-Oriented Over-the-Air Computation for Edge-Device Co-Inference With Balanced Classification Accuracy
- 4 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (11) , 17818-17823
Abstract
Edge-device co-inference, which concerns the cooperation between edge devices and an edge server for completing inference tasks over wireless networks, has been a promising technique for enabling various kinds of intelligent services at the network edge, e.g., auto-driving. In this paradigm, the concerned design objective of the network shifts from the traditional communication throughput to the effective and efficient execution of the inference task underpinned by the network, measured by, e.g., the inference accuracy and latency. In this paper, a task-oriented over-the-air computation scheme is proposed for a multi-device artificial intelligence system. Particularly, a novel tractable inference accuracy metric is proposed for classification tasks, which is called minimum pair-wise discriminant gain. Unlike prior work measuring the average of all class pairs in feature space, it measures the minimum distance of all class pairs. By maximizing the minimum pair-wise discriminant gain instead of its average counterpart, any pair of classes can be better separated in the feature space, and thus leading to a balanced and improved inference accuracy for all classes. Besides, this paper jointly optimizes the minimum discriminant gain of all feature elements instead of separately maximizing that of each element in the existing designs. As a result, the transmit power can be adaptively allocated to the feature elements according to their different contributions to the inference accuracy, opening an extra degree of freedom to improve inference performance. Extensive experiments are conducted using a concrete use case of human motion recognition to verify the superiority of the proposed design over the benchmarking scheme.Keywords
All Related Versions
Funding Information
- Shanghai Sailing Program (23YF1427400)
- National Natural Science Foundation of China (62371313)
- Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515010109)
- Shenzhen-Hong Kong-Macau Technology Research Programme (SGDX20230821091559018)
- Longgang District Special Funds for Science and Technology Innovation (LGKCSDPT2023002)
- National Natural Science Foundation of China (62271318)
- Shanghai Rising-Star Program (22QA1406100)
This publication has 19 references indexed in Scilit:
- Task-Oriented Communications for 6G: Vision, Principles, and TechnologiesIEEE Wireless Communications, 2023
- Gradient and Channel Aware Dynamic Scheduling for Over-the-Air Computation in Federated Edge Learning SystemsIEEE Journal on Selected Areas in Communications, 2023
- Optimized Power Control Design for Over-the-Air Federated Edge LearningIEEE Journal on Selected Areas in Communications, 2021
- Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and ApplicationsIEEE Journal on Selected Areas in Communications, 2021
- Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model2021
- Reconfigurable Intelligent Surface for Green Edge InferenceIEEE Transactions on Green Communications and Networking, 2021
- Communication-Computation Trade-off in Resource-Constrained Edge InferenceIEEE Communications Magazine, 2020
- Device Scheduling with Fast Convergence for Wireless Federated Learning2020
- MIMO Over-the-Air Computation for High-Mobility Multimodal SensingIEEE Internet of Things Journal, 2018
- Optimizing Unlicensed Spectrum Sharing for LTE-U and WiFi Network CoexistenceIEEE Journal on Selected Areas in Communications, 2016