ABSTRACT
We are now in an information era and the volume of data is growing explosively. However, due to privacy issues, it is very common that data cannot be freely shared among the data-generating devices. Federated analytics was recently proposed aiming at deriving analytical insights among data-generating devices without exposing the raw data, but the intermediate analytics results. Note that computing resources at the data-generating devices are limited, thus making on-device execution of computing-intensive tasks challenging. In this chapter, we thus introduce how to apply the digital twin technique, which emulates the resource-limited physical/end side, while utilizing the rich resource at the virtual/computing side. Nevertheless, how to use the digital twin technique to assist federated analytics while preserving distributed data privacy is challenging. To address such a challenge, this chapter formulates a problem on digital twin–assisted federated distribution discovery and introduces a federated Markov Chain Monte Carlo with a delayed rejection method to estimate the representative parameters of global distribution. The corresponding evaluation results are illustrated. In addition, some potential topics on digital twin–enabled federated analytics applications are discussed as well.
