Dynamic Early Exit Scheduling for Deep Neural Network Inference through Contextual Bandits.
Weiyu Ju|Wei Bao|Liming Ge|Dong Yuan
| Anthology ID: | DBLP:conf/cikm/JuBGY21 |
|---|---|
| Volume: | CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021 |
| Year: | 2021 |
| Venue: | International Conference on Information and Knowledge Management (CIKM) |
| Publisher: | ACM |
| Pages: | 823-832 |
| URL: | https://doi.org/10.1145/3459637.3482335 |
| DOI: | https://doi.org/10.1145/3459637.3482335 |
| DBLP: | conf/cikm/JuBGY21 |
| BibTeX: |
@inproceedings{ju-2021-dynamic,
author = {Weiyu Ju and
Wei Bao and
Liming Ge and
Dong Yuan},
editor = {Gianluca Demartini and
Guido Zuccon and
J. Shane Culpepper and
Zi Huang and
Hanghang Tong},
title = {{Dynamic Early Exit Scheduling for Deep Neural Network Inference through Contextual Bandits}},
booktitle = {{CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021}},
pages = {823--832},
publisher = {ACM},
year = {2021},
url = {https://doi.org/10.1145/3459637.3482335},
doi = {https://doi.org/10.1145/3459637.3482335}
}