AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices
Yuzhan Wang, Sicong Liu, Bin Guo, Boqi Zhang, Ke Ma, Yasan Ding, Hao, Luo, Yao Li, Zhiwen Yu

TL;DR
AdaScale is an automated framework that dynamically adapts deep neural networks to mobile device contexts, improving performance, accuracy, and energy efficiency through resource-aware optimization.
Contribution
It introduces a self-evolutionary model and automated adaptation loop for efficient, context-aware DNN scaling on mobile devices.
Findings
Increases accuracy by 5.09%
Reduces training overhead by 66.89%
Speeds up inference latency by 1.51 to 6.2 times
Abstract
Deep learning is reshaping mobile applications, with a growing trend of deploying deep neural networks (DNNs) directly to mobile and embedded devices to address real-time performance and privacy. To accommodate local resource limitations, techniques like weight compression, convolution decomposition, and specialized layer architectures have been developed. However, the \textit{dynamic} and \textit{diverse} deployment contexts of mobile devices pose significant challenges. Adapting deep models to meet varied device-specific requirements for latency, accuracy, memory, and energy is labor-intensive. Additionally, changing processor states, fluctuating memory availability, and competing processes frequently necessitate model re-compression to preserve user experience. To address these issues, we introduce AdaScale, an elastic inference framework that automates the adaptation of deep models…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsContext-Aware Activity Recognition Systems
MethodsConvolution
