| Title: |
Late breaking results: adaptive ensembles of dynamic DNNs for collaborative edge inference |
| Authors: |
Hu, Mingyu; Singh, Amit Kumar; Hare, Jonathon; Merrett, Geoff |
| Publisher Information: |
IEEE |
| Publication Year: |
2026 |
| Collection: |
University of Southampton: e-Prints Soton |
| Description: |
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. |
| Document Type: |
conference object |
| File Description: |
text |
| Language: |
English |
| Relation: |
https://eprints.soton.ac.uk/509859/1/DATE2026_LBR_AdaEnsemble_Mingyu.pdf; 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) |
| Availability: |
https://eprints.soton.ac.uk/509859/; https://eprints.soton.ac.uk/509859/1/DATE2026_LBR_AdaEnsemble_Mingyu.pdf |
| Rights: |
cc_by_4 |
| Accession Number: |
edsbas.EC42562A |
| Database: |
BASE |