SmartSplit: Latency-Energy-Memory Optimisation for CNN Splitting on Smartphone Environment

no code implementations • 1 Nov 2021 • Ishan Prakash, Aniruddh Bansal, Rohit Verma, Rajeev Shorey

In this paper, we analyse the feasibility of splitting CNNs between smartphones and cloud server by formulating a multi-objective optimisation problem that optimises the end-to-end latency, memory utilisation, and energy consumption.

FedFm: Towards a Robust Federated Learning Approach For Fault Mitigation at the Edge Nodes

no code implementations • 1 Nov 2021 • Manupriya Gupta, Pavas Goyal, Rohit Verma, Rajeev Shorey, Huzur Saran

In this paper, 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.

Federated Learning

Latency-Memory Optimized Splitting of Convolution Neural Networks for Resource Constrained Edge Devices

no code implementations • 19 Jul 2021 • Tanmay Jain, Avaneesh, Rohit Verma, Rajeev Shorey

Splitting the CNN architecture to perform part of the computation on edge and remaining on the cloud is an area of research that has seen increasing interest in the field.