Towards Edge-Cloud Collaborative Machine Learning: A Quality-aware Task Partition Framework

Abstract

Edge-cloud collaborative tasks with real-world services emerge in recent years and attract worldwide attention. Unfortunately, state-of-the-art edge-cloud collaborative machine-learning services are still not that reliable due to the data heterogeneity on the edge, where we usually have access to a mixed-up training set, which is intrinsically collected from various distributions of underlying tasks. Finding such hidden tasks that need to be revealed from given datasets is called the Task Partition problem. Manual task partition is usually expensive, unscalable, and biased. Accordingly, we propose Quality-aware Task Partition (QTP) problem, in which final tasks are partitioned by the performance of task models. To the best of our knowledge, this work is the first one to study the QTP problem with an emphasis on task quality. We also implement a public service, HiLens on Huawei Cloud, to support the whole process. We develop a polynomial-time algorithm namely the Task-Forest algorithm (TForest). TForest shows its superiority based on a case study with 57 real-world cameras. Compared with STOA baselines, TForest has on average 9.2% higher F1-scores and requires 43.1% fewer samples when deploying new cameras. Partial code of the framework has been adopted and released to KubeEdge-Sedna.