Noise Is Useful: Exploiting Data Diversity for Edge Intelligence

Edge intelligence requires to fast access distributed data samples generated by edge devices. The challenge is using limited radio resource to acquire massive data samples for training machine learning models at edge server. In this article, we propose a new communication-efficient edge intelligence scheme where the most useful data samples are selected to train the model. Here the usefulness or values of data samples is measured by data diversity which is defined as the difference between data samples. We derive a close-form expression of data diversity that combines data informativeness and channel quality. Then a joint data-and-channel diversity aware multiuser scheduling algorithm is proposed. We find that noise is useful for enhancing data diversity under some conditions.

[1]  Quoc V. Le,et al.  Adding Gradient Noise Improves Learning for Very Deep Networks , 2015, ArXiv.

[2]  Tommaso Melodia,et al.  Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey , 2019, Ad Hoc Networks.

[3]  Jun Zhang,et al.  Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learning , 2019, IEEE Transactions on Cognitive Communications and Networking.

[4]  K. B. Letaief,et al.  A Survey on Mobile Edge Computing: The Communication Perspective , 2017, IEEE Communications Surveys & Tutorials.

[5]  David Cohn,et al.  Active Learning , 2010, Encyclopedia of Machine Learning.

[6]  Karen Drukker,et al.  A study of the effect of noise injection on the training of artificial neural networks , 2009, 2009 International Joint Conference on Neural Networks.

[7]  Mehdi Bennis,et al.  Wireless Network Intelligence at the Edge , 2018, Proceedings of the IEEE.

[8]  Xu Chen,et al.  Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing , 2019, Proceedings of the IEEE.

[9]  Ursula Challita,et al.  Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial , 2017, IEEE Communications Surveys & Tutorials.

[10]  Mengyu Liu,et al.  Price-Based Distributed Offloading for Mobile-Edge Computing With Computation Capacity Constraints , 2017, IEEE Wireless Communications Letters.

[11]  Kaibin Huang,et al.  Multiuser Computation Offloading and Downloading for Edge Computing With Virtualization , 2018, IEEE Transactions on Wireless Communications.

[12]  Yuan Liu,et al.  Data-Importance Aware Radio Resource Allocation: Wireless Communication Helps Machine Learning , 2020, IEEE Communications Letters.