YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers

• Published in: 2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) pp. 285 - 297
• Main Authors: Kwon, Young D., Chauhan, Jagmohan, Mascolo, Cecilia
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2022
• Subjects: Deep learning; Energy consumption; Internet of Things; Microcontrollers; Multi Task Learning; Multitasking; Neural networks; Product Quantization; Switches; Task analysis
• DOI: 10.1109/IPSN54338.2022.00030

Internet of Things (IoT) systems provide large amounts of data on all aspects of human behavior. Machine learning techniques, especially deep neural networks (DNN), have shown promise in making sense of this data at a large scale. Also, the research community has worked to reduce the computational and resource demands of DNN to compute on low-resourced micro controllers (MCUs). However, most of the current work in embedded deep learning focuses on solving a single task efficiently, while the multi-tasking nature and applications of IoT devices demand systems that can handle a diverse range of tasks (such as activity, gesture, voice, and context recognition) with input from a variety of sensors, simultaneously. In this paper, we propose YONO, a product quantization (PQ) based approach that compresses multiple heterogeneous models and enables in-memory model execution and model switching for dissimilar multi-task learning on MCUs. We first adopt PQ to learn codebooks that store weights of different models. Also, we propose a novel network optimization and heuristics to maximize the com-pression rate and minimize the accuracy loss. Then, we develop an online component of YONO for efficient model execution and switching between multiple tasks on an MCU at run time without relying on an external storage device. YONO shows remarkable performance as it can compress multiple heterogeneous models with negligible or no loss of accuracy up to 12.37x. Furthermore, YONO's online component enables an efficient execution (latency of 16-159 ms and energy consumption of 3.8-37.9 mJ per operation) and reduces modelloading/switching la-tency and energy consumption by 93.3-94.5% and 93.9-95.0%, respectively, compared to external storage access. Interestingly, YONO can compress various architectures trained with datasets that were not shown during YONO's offline codebook learning phase showing the generalizability of our method. To summarize, YONO shows great potential and opens further doors to enable multi-task learning systems on extremely resource-constrained devices.