Ricerc@Sapienza

According to the mainstream of the Sixth Generation (6G) communication paradigm, the incoming IoT big data era requires efficient and resource-saving mining of large sets of distributed data through the seamless integration of heterogeneous terrestrial and aerial (e.g., drone supported) wireless subnetworks. To this end, a viable approach could be to attempt to resort to the synergic exploitation of two emerging paradigms, namely, Deep Neural Networks (DNNs) with early exits and Fog Computing (FC). From an IoT perspective, the most appealing feature of DNNs is their hierarchical layer-wise organization, potentially matching the hierarchical organization of the underlying Fog-supported execution platform. However, both the training and inference phases of current DNNs are too cumbersome to be executed by IoT devices, and their remote and centralized implementation induces large communication delays and is bandwidth-wasting. Motivated by these considerations, this proposal plans the activity for the SECOND year of the (two-year) "DeepFog" project. The project aims at developing the integration of the emerging paradigms of the Conditional DNNs (CDNNs) with early exits and FC. For this purpose, the exploitation of the powerful and recent paradigm of Federated Learning (FL) is also exploited for the distributed and asynchronous Fog-supported (and, possibly, drone-aided) training of the underlying CDNN under resource and fairness constraints. Overall, according to the 6G vision, main goals of the DeepFog-2 project are to complete the design and validate in SW the related algorithms already developed during the FIRST research year, by focusing on the:
- formalization of the main building blocks and functionalities of the overall DeepFog technological platform;
- design of a novel asynchronous fast-adaptive FL protocol for the training of CDNNs for Fog supported IoT stream applications;
- design and implementation of the Flying Federated Learning (FFL) toolbox.