Supervised Compression for Split Computing
Summary
Split computing has been attracting attentions from the research community as an intermediate option between local (mobile) computing and full computation offloading. This approach is effective especially for resource-constrained edge computing systems e.g., computationally weak mobile devices, limited wireless communication capacity. We proposed introducing bottleneck (splitting point) to deep learning models at their early stages so that we can minimize local computing and data communication costs while maximizing model accuracy, which we formulated later as supervised compression for split computing (SC2).
We define supervised compression as learning compressed representations for supervised downstream tasks. It is very challenging to introduce bottlenecks (splitting points) to deep learning models at their early layers while preserving model accuracy. SC2 is a key to achieve efficient and accuracy machine learning applications for resource-constrained edge computing systems.
ML OSS
To facilitate research on supervised compression for split computing (SC2), I published an installable Python package named sc2bench (i.e., "pip3 install sc2bench") and a code repository to reproduce the experimental results reported in our SC2 paper.
Related Publications
A Multi-task Supervised Compression Model for Split Computing
WACV 2025
This work was done prior to joining Spiffy AI.
Preprint CodeSC2 Benchmark: Supervised Compression for Split Computing
Transactions on Machine Learning Research (TMLR)
This work was done prior to joining Amazon.
OpenReview Video Preprint Code PyPISplitBeam: Effective and Efficient Beamforming in Wi-Fi Networks Through Split Computing
ICDCS 2023
This work was done prior to joining Amazon.
Paper Preprint Code DatasetSplit Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
ACM Computing Surveys (CSUR)
Supervised Compression for Resource-Constrained Edge Computing Systems
WACV 2022
Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
ICPR 2020
Optimal Task Allocation for Time-Varying Edge Computing Systems with Split DNNs
IEEE GLOBECOM 2020
Split Computing for Complex Object Detectors: Challenges and Preliminary Results
MobiCom 2020 Workshop on Embedded and Mobile Deep Learning (EMDL)