@inproceedings{e16d5f9fad0e41ccb0cf758bdb4dc4cd,
title = "Poster Abstract: Xpi: Real-Time Progressive Inference Serving with Explainable AI in Edge-Cloud Systems",
abstract = "The constrained computing and memory resources at the edge pose challenges for satisfying different service-level objectives (SLOs) of deep learning inference requests. In this paper, we propose a novel edge-cloud progressive inference framework Xpi, which integrates explainable AI technique to facilitate early-exit, and learning-based online execution control to satisfy different SLOs and optimize edge resource overheads. We implement Xpi on an edge-cloud platform, and conduct partial experiments on two datasets. Xpi outperforms several advanced edge-cloud progressive inference frameworks in terms of accuracy and deadline satisfaction rate.",
keywords = "edge computing, explainable AI, progressive inference, reinforcement learning",
author = "Changyao Lin and Zhenming Chen and Jie Liu",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 23rd ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2024 ; Conference date: 13-05-2024 Through 16-05-2024",
year = "2024",
doi = "10.1109/IPSN61024.2024.00037",
language = "英语",
series = "Proceedings - 23rd ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2024",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "273--274",
booktitle = "Proceedings - 23rd ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2024",
address = "美国",
}