{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:10:33Z","timestamp":1767262233886,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543873.3587370","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"302-305","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Deep Neural Network Inference for Device-Edge-Cloud Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0173-7544","authenticated-orcid":false,"given":"Fatih","family":"Ilhan","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8662-3609","authenticated-orcid":false,"given":"Selim Furkan","family":"Tekin","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3297-6991","authenticated-orcid":false,"given":"Sihao","family":"Hu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4557-1865","authenticated-orcid":false,"given":"Tiansheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5917-2577","authenticated-orcid":false,"given":"Ka-Ho","family":"Chow","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4138-3082","authenticated-orcid":false,"given":"Ling","family":"Liu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517857"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1."},{"key":"e_1_3_2_1_4_1","unstructured":"Sayan Ghosh Karthik Prasad Xiaoliang Dai Peizhao Zhang Bichen Wu Graham Cormode and Peter Vajda. 2022. Pruning Compact ConvNets For Efficient Inference."},{"key":"e_1_3_2_1_5_1","volume-title":"Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William\u00a0J. Dally. 2016. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR 2016."},{"key":"e_1_3_2_1_6_1","volume-title":"Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 770\u2013778."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. https:\/\/doi.org\/10.48550\/ARXIV.1503.02531","DOI":"10.48550\/ARXIV.1503.02531"},{"key":"e_1_3_2_1_8_1","volume-title":"Multi-Scale Dense Networks for Resource Efficient Image Classification. In International Conference on Learning Representations.","author":"Huang Gao","year":"2018","unstructured":"Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van\u00a0der Maaten, and Kilian Weinberger. 2018. Multi-Scale Dense Networks for Resource Efficient Image Classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469116.3470012"},{"key":"e_1_3_2_1_10_1","volume-title":"Improved Techniques for Training Adaptive Deep Networks. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","author":"Li Hao","year":"2019","unstructured":"Hao Li, Hong Zhang, Xiaojuan Qi, Ruigang Yang, and Gao Huang. 2019. Improved Techniques for Training Adaptive Deep Networks. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 1891\u20131900."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"volume-title":"2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).","author":"Teerapittayanon Surat","key":"e_1_3_2_1_12_1","unstructured":"Surat Teerapittayanon, Bradley McDanel, and H.T. Kung. 2017. Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices. In 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)."},{"key":"e_1_3_2_1_13_1","unstructured":"Xiang Zhang Junbo Zhao and Yann LeCun. 2015. Character-level CNNs for Text Classification. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_14_1","unstructured":"Wangchunshu Zhou Canwen Xu Tao Ge Julian McAuley Ke Xu and Furu Wei. 2020. BERT Loses Patience: Fast and Robust Inference with Early Exit. In Advances in Neural Information Processing Systems."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Austin TX USA","acronym":"WWW '23"},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587370","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3587370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:33:35Z","timestamp":1755819215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587370"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":14,"alternative-id":["10.1145\/3543873.3587370","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3587370","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}