MDInference: Balancing Inference Accuracy and Latency for Mobile Applications
share
Deep Neural Networks (DNNs) are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them efficiently on resource-constrained mobile devices. Prior work has begun to approach the problem of supporting deep learning in mobile applications by either decreasing execution latency or utilizing powerful cloud servers. These approaches only focus on single aspects of mobile inference and thus they often sacrifice other aspects. In this work we introduce a holistic approach to designing mobile deep inference frameworks. We first identify the key goals of accuracy and latency for mobile deep inference, and the conditions that must be met to achieve them. We demonstrate our holistic approach through the design of a hypothetical framework called MDInference. This framework leverages two complementary techniques; a model selection algorithm that chooses from a set of cloud-based deep learning models to improve accuracy and an on-device request duplication mechanism to bound latency. Through empirically-driven simulations we show that MDInference improves aggregate accuracy over static approaches by 40 incurring SLA violations. Additionally, we show that with SLA = 250ms, MDInference can increase the aggregate accuracy in 99.74 university networks and 96.84
READ FULL TEXT