MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge

Cascade systems comprise a two-model sequence, a lightweight model processing all samples and a heavier model conditionally refining harder samples to improve accuracy. By placing the light model on the device side and the heavy model on a server, model cascades constitute a widely used distributed...

Full description

Saved in:
Bibliographic Details
Main Authors: Nikolaidis, Sokratis, Venieris, Stylianos I., Venieris, Iakovos S.
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Collaboration
Computers
Performance evaluation
Refining
Scalability
Throughput
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cascade systems comprise a two-model sequence, a lightweight model processing all samples and a heavier model conditionally refining harder samples to improve accuracy. By placing the light model on the device side and the heavy model on a server, model cascades constitute a widely used distributed inference approach. With the rapid expansion of intelligent indoor environments, the new setting of Multi-Device Cascade is emerging where multiple and diverse devices are simultaneously using a shared heavy model on the same server, typically located close to the consumer environment. This work presents Multi-TASC, a multi-tenancy-aware scheduler that adaptively controls the forwarding decision functions of the devices in order to maximize the system throughput, while sustaining high accuracy and low latency. By explicitly considering device heterogeneity, our scheduler improves the latency service-level objective (SLO) satisfaction rate over state-of-the-art cascade methods in highly heterogeneous setups, while serving over 40 devices, showcasing its scalability.
ISSN:2642-7389
DOI:10.1109/ISCC58397.2023.10217872