ECCENTRIC: Edge-Cloud Collaboration Framework for Distributed Inference Using Knowledge Adaptation
By: Mohammad Mahdi Kamani, Zhongwei Cheng, Lin Chen
Potential Business Impact:
Makes smart devices faster and use less power.
The massive growth in the utilization of edge AI has made the applications of machine learning models ubiquitous in different domains. Despite the computation and communication efficiency of these systems, due to limited computation resources on edge devices, relying on more computationally rich systems on the cloud side is inevitable in most cases. Cloud inference systems can achieve the best performance while the computation and communication cost is dramatically increasing by the expansion of a number of edge devices relying on these systems. Hence, there is a trade-off between the computation, communication, and performance of these systems. In this paper, we propose a novel framework, dubbed as Eccentric that learns models with different levels of trade-offs between these conflicting objectives. This framework, based on an adaptation of knowledge from the edge model to the cloud one, reduces the computation and communication costs of the system during inference while achieving the best performance possible. The Eccentric framework can be considered as a new form of compression method suited for edge-cloud inference systems to reduce both computation and communication costs. Empirical studies on classification and object detection tasks corroborate the efficacy of this framework.
Similar Papers
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
Distributed, Parallel, and Cluster Computing
Makes smart apps run faster on phones and clouds.
A Confidence-Constrained Cloud-Edge Collaborative Framework for Autism Spectrum Disorder Diagnosis
Networking and Internet Architecture
Helps schools spot autism with better privacy.
Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions
Distributed, Parallel, and Cluster Computing
Makes smart apps run faster and safer.