Computer Science Seminar by Rajeev Shorey: Recent Investigations in Machine Learning and Edge Computing

Speaker: Rajeev Shorey, Formerly CEO, The University of Queensland - IIT Delhi Academy of
Research (UQIDAR), IIT Delhi & Adjunct Faculty, Computer Science & Engineering
Department, IIT Delhi, India

Title: Recent Investigations in Machine Learning and Edge Computing

Abstract: In this talk, we highlight the research challenges in the intersection of Machine
Learning and Edge Computing.  More specifically, we look at the Federated Learning paradigm
in a faulty edge ecosystem.
Federated Learning deviates from the norm of ”send data to model” to ”send model to data''.
When used in an edge ecosystem, numerous heterogeneous edge devices collecting data
through different means and connected through different network channels get involved in the
training process. Failure of edge devices in such an ecosystem due to device fault or network
issues are highly likely.
In this talk, we first analyse the impact of the number of edge devices on an FL model and
provide a strategy to select an optimal number of devices that would contribute to the model.
We observe the impact of data distribution on the number of optimal devices. We then
investigate how the edge ecosystem behaves when the selected devices fail and provide a
mitigation strategy to ensure a robust Federated Learning technique. Finally, we design a real-
world application to highlight the impact of the designed mitigation strategy.
The talk will end with a brief discussion of several open research problems in the intersection of
Machine Learning and Edge Computing.