Power Control for NN-Based Wireless Distributed Inference With Improved Model Calibration
- 27 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (10) , 14591-14604
Abstract
In recent years, the application of neural networks (NNs) in wireless communication has garnered widespread attention and proven successful. However, conventional learning-based NNs often suffer from poor calibration, meaning that they struggle to reliably quantify prediction confidence and lack proper uncertainty estimation. This limitation becomes especially critical for next generation communication systems, particularly in complex industrial scenarios with stringent reliability requirements. Previous efforts to enhance model calibration have primarily centered on modifying NNs’ training processes. However, these methods often demand significant computing resources, making them impractical for resource-constrained scenarios. In this paper, we investigate a distributed wireless communication system involving multiple users and propose a novel approach to improve model calibration. Our method focuses on enhancing calibration during the inference stage of NNs by introducing a power control mechanism. Notably, existing research indicates that many NNs exhibit overconfidence, i.e., the NN’s confidence exceeds its actual accuracy. Leveraging this insight, we exploit the inherent noise and fading in wireless systems to naturally reduce the NN’s confidence while preserving accuracy. To achieve this, we employ linear relaxation-based perturbation analysis (LiRPA) to approximate the relationship between the perturbed output and the input perturbation of the NN. Subsequently, we devise an optimization problem by leveraging the analyzed relationship and the definition of perfect calibration. It is aimed at finding the input perturbation that maximizes the probability of the model achieving perfect calibration. Finally, considering different channel conditions and a given specific modulation method, we derive the optimal transmission power based on bit error rate (BER) formula. Simulation results demonstrate that our proposed power control method exhibits significant advantages in model calibration compared to several traditional approaches.Keywords
Funding Information
- National Natural Science Foundation of China (U22A2004)
- Zhejiang Provincial Key Laboratory of Information Processing, Communication and Networking (IPCAN), Hangzhou, China
This publication has 14 references indexed in Scilit:
- Calibrating AI Models for Wireless Communications via Conformal PredictionIEEE Transactions on Machine Learning in Communications and Networking, 2023
- Meta-Gating Framework for Fast and Continuous Resource Optimization in Dynamic Wireless EnvironmentsIEEE Transactions on Communications, 2023
- Calibration after bootstrap for accurate uncertainty quantification in regression modelsnpj Computational Materials, 2022
- Improving Calibration for Long-Tailed Recognition2021
- A Fast Graph Neural Network-Based Method for Winner Determination in Multi-Unit Combinatorial AuctionsIEEE Transactions on Cloud Computing, 2020
- A Very Brief Introduction to Machine Learning With Applications to Communication SystemsIEEE Transactions on Cognitive Communications and Networking, 2018
- Deep Power Control: Transmit Power Control Scheme Based on Convolutional Neural NetworkIEEE Communications Letters, 2018
- On Sampling Strategies for Neural Network-based Collaborative Filtering2017
- Algorithmic Learning in a Random World2005
- M-PSK and M-QAM BER computation using signal-space conceptsIEEE Transactions on Communications, 1999