{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:39:55Z","timestamp":1743079195654,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031578076"},{"type":"electronic","value":"9783031578083"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-57808-3_3","type":"book-chapter","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T15:02:05Z","timestamp":1712329325000},"page":"34-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards a\u00a0Flexible Accuracy-Oriented Deep Learning Module Inference Latency Prediction Framework for\u00a0Adaptive Optimization Algorithms"],"prefix":"10.1007","author":[{"given":"Jingran","family":"Shen","sequence":"first","affiliation":[]},{"given":"Nikos","family":"Tziritas","sequence":"additional","affiliation":[]},{"given":"Georgios","family":"Theodoropoulos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,6]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Banitalebi-Dehkordi, A., Vedula, N., Pei, J., Xia, F., Wang, L., Zhang, Y.: Auto-split: a general framework of collaborative edge-cloud AI. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. p. 2543-2553. KDD 2021, Association for Computing Machinery (2021). https:\/\/doi.org\/10.1145\/3447548.3467078","DOI":"10.1145\/3447548.3467078"},{"key":"3_CR2","unstructured":"Bank, D., Koenigstein, N., Giryes, R.: Autoencoders (2021)"},{"key":"3_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners (2020)"},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Hu, C., Li, B.: Distributed inference with deep learning models across heterogeneous edge devices. In: IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, pp. 330\u2013339 (2022). https:\/\/doi.org\/10.1109\/INFOCOM48880.2022.9796896","DOI":"10.1109\/INFOCOM48880.2022.9796896"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Kum, S., Oh, S., Yeom, J., Moon, J.: Optimization of edge resources for deep learning application with batch and model management. Sensors 22(17) (2022). https:\/\/doi.org\/10.3390\/s22176717, https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6717","DOI":"10.3390\/s22176717"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"69680","DOI":"10.1109\/ACCESS.2022.3187002","volume":"10","author":"A Lahiany","year":"2022","unstructured":"Lahiany, A., Aperstein, Y.: Pteenet: post-trained early-exit neural networks augmentation for inference cost optimization. IEEE Access 10, 69680\u201369687 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3187002","journal-title":"IEEE Access"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Li, E., Zeng, L., Zhou, Z., Chen, X.: Edge AI: on-demand accelerating deep neural network inference via edge computing (2019)","DOI":"10.1109\/TWC.2019.2946140"},{"issue":"2","key":"3_CR9","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TSC.2021.3109094","volume":"15","author":"P Lin","year":"2022","unstructured":"Lin, P., Shi, Z., Xiao, Z., Chen, C., Li, K.: Latency-driven model placement for efficient edge intelligence service. IEEE Trans. Serv. Comput. 15(2), 591\u2013601 (2022). https:\/\/doi.org\/10.1109\/TSC.2021.3109094","journal-title":"IEEE Trans. Serv. Comput."},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Liu, G., Dai, F., Huang, B., Li, L., Wang, S., Qiang, Z.: Towards accurate latency prediction of DNN layers inference on diverse computing platforms. In: 2022 IEEE International Conference on Dependable, Autonomic and Secure Computing, International Conference on Pervasive Intelligence and Computing, International Conference on Cloud and Big Data Computing, International Conference on Cyber Science and Technology Congress (DASC\/PiCom\/CBDCom\/CyberSciTech), pp.\u00a01\u20137 (2022). https:\/\/doi.org\/10.1109\/DASC\/PiCom\/CBDCom\/Cy55231.2022.9927862","DOI":"10.1109\/DASC\/PiCom\/CBDCom\/Cy55231.2022.9927862"},{"key":"3_CR11","doi-asserted-by":"publisher","unstructured":"Mao, J., Chen, X., Nixon, K.W., Krieger, C., Chen, Y.: MoDNN: local distributed mobile computing system for deep neural network. In: Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017. pp. 1396\u20131401 (2017). https:\/\/doi.org\/10.23919\/DATE.2017.7927211","DOI":"10.23919\/DATE.2017.7927211"},{"key":"3_CR12","unstructured":"Mendoza, D.: Predicting latency of neural network inference (2020)"},{"key":"3_CR13","unstructured":"Paszke, A., et al.: PyTorch: An Imperative Style. High-Performance Deep Learning Library. Curran Associates Inc., Red Hook (2019)"},{"key":"3_CR14","unstructured":"Shao, J., Zhang, H., Mao, Y., Zhang, J.: Branchy-GNN: a device-edge co-inference framework for efficient point cloud processing (2023)"},{"issue":"1","key":"3_CR15","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1109\/TWC.2022.3192613","volume":"22","author":"W Shi","year":"2023","unstructured":"Shi, W., Zhou, S., Niu, Z., Jiang, M., Geng, L.: Multiuser co-inference with batch processing capable edge server. IEEE Trans. Wireless Commun. 22(1), 286\u2013300 (2023). https:\/\/doi.org\/10.1109\/TWC.2022.3192613","journal-title":"IEEE Trans. Wireless Commun."},{"issue":"12","key":"3_CR16","doi-asserted-by":"publisher","first-page":"9511","DOI":"10.1109\/JIOT.2020.3010258","volume":"8","author":"X Tang","year":"2021","unstructured":"Tang, X., Chen, X., Zeng, L., Yu, S., Chen, L.: Joint multiuser DNN partitioning and computational resource allocation for collaborative edge intelligence. IEEE Internet Things J. 8(12), 9511\u20139522 (2021). https:\/\/doi.org\/10.1109\/JIOT.2020.3010258","journal-title":"IEEE Internet Things J."},{"key":"3_CR17","doi-asserted-by":"publisher","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.: Distributed deep neural networks over the cloud, the edge and end devices. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), pp. 328\u2013339 (2017). https:\/\/doi.org\/10.1109\/ICDCS.2017.226","DOI":"10.1109\/ICDCS.2017.226"},{"issue":"2","key":"3_CR18","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TNET.2020.3042320","volume":"29","author":"L Zeng","year":"2021","unstructured":"Zeng, L., Chen, X., Zhou, Z., Yang, L., Zhang, J.: Coedge: cooperative DNN inference with adaptive workload partitioning over heterogeneous edge devices. IEEE\/ACM Trans. Networking 29(2), 595\u2013608 (2021). https:\/\/doi.org\/10.1109\/TNET.2020.3042320","journal-title":"IEEE\/ACM Trans. Networking"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Zhang, L.L., et al.: NN-meter: towards accurate latency prediction of deep-learning model inference on diverse edge devices. In: Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services. MobiSys 2021, New York, NY, USA, pp. 81-93. Association for Computing Machinery (2021). https:\/\/doi.org\/10.1145\/3458864.3467882, https:\/\/doi.org\/10.1145\/3458864.3467882","DOI":"10.1145\/3458864.3467882 10.1145\/3458864.3467882"}],"container-title":["IFIP Advances in Information and Communication Technology","Intelligent Information Processing XII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-57808-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T15:02:34Z","timestamp":1712329354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-57808-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031578076","9783031578083"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-57808-3_3","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"6 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mi.hitsz.edu.cn\/iip2024.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair online submission","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"84% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7 Abstracts include 4 Keynotes speakers and 3 Invited Speakers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}