The University of Southampton
University of Southampton Institutional Repository

Late breaking results: adaptive ensembles of dynamic DNNs for collaborative edge inference

Late breaking results: adaptive ensembles of dynamic DNNs for collaborative edge inference
Late breaking results: adaptive ensembles of dynamic DNNs for collaborative edge inference
Edge computing enables low-latency and privacy-preserving DNN inference, yet heterogeneous and dynamically changing device resources make it difficult to satisfy real-time constraints. In this paper, we present AdaEnsemble, an adaptive and collaborative ensemble inference framework that integrates Dynamic DNNs with deadline-aware scheduling. The system profiles accuracy and latency offline and selects both model widths and participating devices at runtime to maximize accuracy under a given deadline. Experiments on heterogeneous edge devices show that AdaEnsemble adapts effectively to different latency requirements and consistently outperforms the state-of-art.
IEEE
Hu, Mingyu
686551f3-f76b-471d-b424-71a5c68851da
Singh, Amit Kumar
c66ea877-9566-4279-87a7-717d3c1406ed
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Merrett, Geoff
89b3a696-41de-44c3-89aa-b0aa29f54020
Hu, Mingyu
686551f3-f76b-471d-b424-71a5c68851da
Singh, Amit Kumar
c66ea877-9566-4279-87a7-717d3c1406ed
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Merrett, Geoff
89b3a696-41de-44c3-89aa-b0aa29f54020

Hu, Mingyu, Singh, Amit Kumar, Hare, Jonathon and Merrett, Geoff (2026) Late breaking results: adaptive ensembles of dynamic DNNs for collaborative edge inference. In Design, Automation and Test in Europe Conference 2026. IEEE. 3 pp . (In Press)

Record type: Conference or Workshop Item (Paper)

Abstract

Edge computing enables low-latency and privacy-preserving DNN inference, yet heterogeneous and dynamically changing device resources make it difficult to satisfy real-time constraints. In this paper, we present AdaEnsemble, an adaptive and collaborative ensemble inference framework that integrates Dynamic DNNs with deadline-aware scheduling. The system profiles accuracy and latency offline and selects both model widths and participating devices at runtime to maximize accuracy under a given deadline. Experiments on heterogeneous edge devices show that AdaEnsemble adapts effectively to different latency requirements and consistently outperforms the state-of-art.

Text
Late Breaking Results: Adaptive Ensembles of Dynamic DNNs for Collaborative Edge Inference - Accepted Manuscript
Restricted to Repository staff only until 22 April 2026.
Available under License Creative Commons Attribution.
Request a copy

More information

Accepted/In Press date: 13 January 2026
Venue - Dates: 2026 Design, Automation & Test in Europe Conference, , Verona, Italy, 2026-04-20 - 2026-04-22

Identifiers

Local EPrints ID: 509859
URI: http://eprints.soton.ac.uk/id/eprint/509859
PURE UUID: 58d6adc5-d44b-4f92-9b2f-4e6c554a1855
ORCID for Jonathon Hare: ORCID iD orcid.org/0000-0003-2921-4283
ORCID for Geoff Merrett: ORCID iD orcid.org/0000-0003-4980-3894

Catalogue record

Date deposited: 09 Mar 2026 17:36
Last modified: 10 Mar 2026 02:42

Export record

Contributors

Author: Mingyu Hu
Author: Amit Kumar Singh
Author: Jonathon Hare ORCID iD
Author: Geoff Merrett ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×