Abstract | ||
---|---|---|
Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices. A popular alternative comprises offloading CNN processing to powerful cloud-based servers. Nevertheless, by relying on the cloud to produce outputs, emerging mission-critical and high-mobility applications, such as drone obstacle avoidance or interactive applications, can suffer from the dynamic connectivity conditions and the uncertain availability of the cloud. In this paper, we propose SPINN, a distributed inference system that employs synergistic device-cloud computation together with a progressive inference method to deliver fast and robust CNN inference across diverse settings. The proposed system introduces a novel scheduler that co-optimises the early-exit policy and the CNN splitting at run time, in order to adapt to dynamic conditions and meet user-defined service-level requirements. Quantitative evaluation illustrates that SPINN outperforms its state-of-the-art collaborative inference counterparts by up to 2× in achieved throughput under varying network conditions, reduces the server cost by up to 6.8× and improves accuracy by 20.7% under latency constraints, while providing robust operation under uncertain connectivity conditions and significant energy savings compared to cloud-centric execution.
|
Year | DOI | Venue |
---|---|---|
2020 | 10.1145/3372224.3419194 | MobiCom '20: The 26th Annual International Conference on Mobile Computing and Networking
London
United Kingdom
September, 2020 |
DocType | ISBN | Citations |
Conference | 978-1-4503-7085-1 | 7 |
PageRank | References | Authors |
0.46 | 27 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stefanos Laskaridis | 1 | 18 | 3.21 |
Stylianos I. Venieris | 2 | 106 | 12.98 |
Mário Almeida | 3 | 12 | 2.62 |
Ilias Leontiadis | 4 | 761 | 44.38 |
Nicholas D. Lane | 5 | 4247 | 248.15 |