FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors
It addresses efficient data labeling for mobile ML training, which is incremental and domain-specific.
The paper tackles the problem of auto-labeling data on mobile devices with non-stationary data and unknown labels, introducing Flame, a system that achieves high labeling accuracy and performance on heterogeneous processors.
How to accurately and efficiently label data on a mobile device is critical for the success of training machine learning models on mobile devices. Auto-labeling data on mobile devices is challenging, because data is usually incrementally generated and there is possibility of having unknown labels. Furthermore, the rich hardware heterogeneity on mobile devices creates challenges on efficiently executing auto-labeling workloads. In this paper, we introduce Flame, an auto-labeling system that can label non-stationary data with unknown labels. Flame includes a runtime system that efficiently schedules and executes auto-labeling workloads on heterogeneous mobile processors. Evaluating Flame with eight datasets on a smartphone, we demonstrate that Flame enables auto-labeling with high labeling accuracy and high performance.