DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
This addresses the problem of limited computational resources and high energy consumption for deep learning on wearables, offering a practical solution for developers and users, though it is incremental as it builds on existing offloading techniques.
The paper tackles the challenge of running deep learning tasks on wearable devices by proposing DeepWear, a framework that adaptively offloads tasks to paired handheld devices via local networks, resulting in up to 5.08x speedup and 53.5% energy savings compared to wearable-only execution.
Due to their on-body and ubiquitous nature, wearables can generate a wide range of unique sensor data creating countless opportunities for deep learning tasks. We propose DeepWear, a deep learning (DL) framework for wearable devices to improve the performance and reduce the energy footprint. DeepWear strategically offloads DL tasks from a wearable device to its paired handheld device through local network. Compared to the remote-cloud-based offloading, DeepWear requires no Internet connectivity, consumes less energy, and is robust to privacy breach. DeepWear provides various novel techniques such as context-aware offloading, strategic model partition, and pipelining support to efficiently utilize the processing capacity from nearby paired handhelds. Deployed as a user-space library, DeepWear offers developer-friendly APIs that are as simple as those in traditional DL libraries such as TensorFlow. We have implemented DeepWear on the Android OS and evaluated it on COTS smartphones and smartwatches with real DL models. DeepWear brings up to 5.08X and 23.0X execution speedup, as well as 53.5% and 85.5% energy saving compared to wearable-only and handheld-only strategies, respectively.