mlsanityData to 14 Oct 2026

Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables

arXiv 2401.08637 ↗First posted 11 Dec 2023cs.DC cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

The advent of tiny artificial intelligence (AI) accelerators enables AI to run at the extreme edge, offering reduced latency, lower power cost, and improved privacy. When integrated into wearable devices, these accelerators open exciting opportunities, allowing various AI apps to run directly on the body. We present Synergy that provides AI apps with best-effort performance via system-driven holistic collaboration over AI accelerator-equipped wearables. To achieve this, Synergy provides device-agnostic programming interfaces to AI apps, giving the system visibility and controllability over the app's resource use. Then, Synergy maximizes the inference throughput of concurrent AI models by creating various execution plans for each app considering AI accelerator availability and intelligently selecting the best set of execution plans. Synergy further improves throughput by leveraging parallelization opportunities over multiple computation units. Our evaluations with 7 baselines and 8 models demonstrate that, on average, Synergy achieves a 23.0 times improvement in throughput, while reducing latency by 73.9% and power consumption by 15.8%, compared to the baselines.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 73 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

19 of 73 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  5. 2016Clipper: A Low-Latency Online Prediction Serving Systemcited by 191
  6. 2020SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloudcited by 112
  7. 2016DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processingcited by 84
  8. 2020CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devicescited by 67
  9. 2020μNAS: Constrained Neural Architecture Search for Microcontrollerscited by 55
  10. 2019SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollerscited by 52
  11. 2019Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollerscited by 33
  12. 2021Auto-Split: A General Framework of Collaborative Edge-Cloud AIcited by 30
7 more
  1. 2016Lets keep it simple, Using simple architectures to outperform deeper and more complex architecturescited by 25
  2. 2023TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollerscited by 18
  3. 2021Differentiable Network Pruning for Microcontrollerscited by 16
  4. 2014The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Veloxcited by 8
  5. 2022DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devicescited by 8
  6. 2020WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodescited by 3
  7. 2023AdaMEC: Towards a Context-Adaptive and Dynamically-Combinable DNN Deployment Framework for Mobile Edge Computingcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 7