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.
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.
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
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
Author:
Geoff Merrett
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