Adaptive and Collaborative Inference: Towards a No-compromise Framework for Distributed Intelligent Systems

Alireza Furutanpey, Schahram Dustdar

2022

Abstract

Deep Neural Networks (DNNs) are the backbone of virtually all complex, intelligent systems. However, networks which achieve state-of-the-art accuracy cannot execute inference tasks within a reasonable time on commodity hardware. Consequently, latency-sensitive mobile and Internet of Things (IoT) applications must compromise by executing a heavily compressed model locally or offloading their inference task to a remote server. Sacrificing accuracy is unacceptable for critical applications, such as anomaly detection. Offloading inference tasks requires ideal network conditions and harbours privacy risks. In this position paper, we introduce a series of planned research work with the overarching aim to provide a (close to) no compromise framework for accurate and fast inference. Specifically, we envision a composition of solutions that leverage the upsides of different computing paradigms while overcoming their downsides through collaboration and adaptive methods that maximise resource efficiency.

Paper Citation

in Harvard Style

Furutanpey A. and Dustdar S. (2022). Adaptive and Collaborative Inference: Towards a No-compromise Framework for Distributed Intelligent Systems. In Proceedings of the 18th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-613-2, pages 144-151. DOI: 10.5220/0011547800003318

in Bibtex Style

@conference{webist22,
author={Alireza Furutanpey and Schahram Dustdar},
title={Adaptive and Collaborative Inference: Towards a No-compromise Framework for Distributed Intelligent Systems},
booktitle={Proceedings of the 18th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2022},
pages={144-151},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011547800003318},
isbn={978-989-758-613-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Adaptive and Collaborative Inference: Towards a No-compromise Framework for Distributed Intelligent Systems
SN - 978-989-758-613-2
AU - Furutanpey A.
AU - Dustdar S.
PY - 2022
SP - 144
EP - 151
DO - 10.5220/0011547800003318