{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:00:39Z","timestamp":1757541639135,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030953874"},{"type":"electronic","value":"9783030953881"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-95388-1_21","type":"book-chapter","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T08:20:55Z","timestamp":1645518055000},"page":"317-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["EdgeSP: Scalable Multi-device Parallel DNN Inference on Heterogeneous Edge Clusters"],"prefix":"10.1007","author":[{"given":"Zhipeng","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijia","family":"Mo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,23]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR2","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1016\/j.future.2020.02.026","volume":"107","author":"K Xiao","year":"2020","unstructured":"Xiao, K., Gao, Z., Shi, W., Qiu, X., Yang, Y., Rui, L.: EdgeABC: an architecture for task offloading and resource allocation in the Internet of Things. Future Gener. Comput. Syst. 107, 498\u2013508 (2020). https:\/\/doi.org\/10.1016\/j.future.2020.02.026","journal-title":"Future Gener. Comput. Syst."},{"issue":"1","key":"21_CR3","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1145\/3093337.3037698","volume":"45","author":"Y Kang","year":"2017","unstructured":"Kang, Y., et al.: Neurosurgeon: collaborative intelligence between the cloud and mobile edge. SIGARCH Comput. Archit. News 45(1), 615\u2013629 (2017). https:\/\/doi.org\/10.1145\/3093337.3037698","journal-title":"SIGARCH Comput. Archit. News"},{"key":"21_CR4","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"},{"key":"21_CR5","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.T.: BranchyNet: fast inference via early exiting from deep neural networks. CoRR abs\/1709.01686 (2017). http:\/\/arxiv.org\/abs\/1709.01686"},{"key":"21_CR6","doi-asserted-by":"publisher","unstructured":"Gao, Z., Miao, D., Zhao, L., Mo, Z., Qi, G., Yan, L.: Triple-partition network: collaborative neural network based on the \u2018end device-edge-cloud\u2019. In: 2021 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1\u20137 (2021). https:\/\/doi.org\/10.1109\/WCNC49053.2021.9417243","DOI":"10.1109\/WCNC49053.2021.9417243"},{"key":"21_CR7","doi-asserted-by":"publisher","unstructured":"Du, J., Shen, M., Du, Y.: A distributed in-situ CNN inference system for IoT applications. In: 2020 IEEE 38th International Conference on Computer Design (ICCD), pp. 279\u2013287 (2020). https:\/\/doi.org\/10.1109\/ICCD50377.2020.00055","DOI":"10.1109\/ICCD50377.2020.00055"},{"issue":"9","key":"21_CR8","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1109\/TPDS.2021.3058532","volume":"32","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Zhang, S., Qian, Z., Wu, J., Jin, Y., Lu, S.: DeepSlicing: collaborative and adaptive CNN inference with low latency. IEEE Trans. Parallel Distrib. Syst. 32(9), 2175\u20132187 (2021)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"21_CR9","doi-asserted-by":"publisher","unstructured":"Mohammed, T., Joe-Wong, C., Babbar, R., Francesco, M.D.: Distributed inference acceleration with adaptive DNN partitioning and offloading. In: IEEE INFOCOM 2020 - IEEE Conference on Computer Communications, pp. 854\u2013863 (2020). https:\/\/doi.org\/10.1109\/INFOCOM41043.2020.9155237","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"21_CR10","doi-asserted-by":"publisher","unstructured":"Xue, F., Fang, W., Xu, W., Wang, Q., Ma, X., Ding, Y.: EdgeLD: locally distributed deep learning inference on edge device clusters. In: 2020 IEEE 22nd International Conference on High Performance Computing and Communications; IEEE 18th International Conference on Smart City; IEEE 6th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 613\u2013619 (2020). https:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS50907.2020.00078","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00078"},{"issue":"2","key":"21_CR11","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. Netw. 29(2), 595\u2013608 (2021). https:\/\/doi.org\/10.1109\/TNET.2020.3042320","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: MeDNN: a distributed mobile system with enhanced partition and deployment for large-scale DNNs. In: 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), pp. 751\u2013756. IEEE (2017)","DOI":"10.1109\/ICCAD.2017.8203852"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, L., Samavatian, M.H., Bacha, A., Majumdar, S., Teodorescu, R.: Adaptive parallel execution of deep neural networks on heterogeneous edge devices. In: Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing, SEC 2019, pp. 195\u2013208. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3318216.3363312","DOI":"10.1145\/3318216.3363312"},{"key":"21_CR14","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"},{"issue":"11","key":"21_CR15","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TCAD.2018.2858384","volume":"37","author":"Z Zhao","year":"2018","unstructured":"Zhao, Z., Barijough, K.M., Gerstlauer, A.: DeepThings: distributed adaptive deep learning inference on resource-constrained IoT edge clusters. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 37(11), 2348\u20132359 (2018)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Fang, B., Zeng, X., Zhang, M.: NestDNN: resource-aware multi-tenant on-device deep learning for continuous mobile vision. In: Proceedings of the 24th Annual International Conference on Mobile Computing and Networking, MobiCom 2018, pp. 115\u2013127. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3241539.3241559","DOI":"10.1145\/3241539.3241559"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Xu, Z., Yut, F., Liu, C., Chen, X.: ReForm: static and dynamic resource-aware DNN reconfiguration framework for mobile device. In: 2019 56th ACM\/IEEE Design Automation Conference (DAC), pp. 1\u20136 (2019)","DOI":"10.1145\/3316781.3324696"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Oh, Y.H., et al.: A portable, automatic data quantizer for deep neural networks. In: Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques, PACT 2018. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3243176.3243180","DOI":"10.1145\/3243176.3243180"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Tan, X., Li, H., Wang, L., Huang, X., Xu, Z.: Empowering adaptive early-exit inference with latency awareness. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 11, pp. 9825\u20139833, May 2021. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17181","DOI":"10.1609\/aaai.v35i11.17181"},{"key":"21_CR20","doi-asserted-by":"publisher","unstructured":"Laskaridis, S., Venieris, S.I., Almeida, M., Leontiadis, I., Lane, N.D.: SPINN: synergistic progressive inference of neural networks over device and cloud. In: Proceedings of the 26th Annual International Conference on Mobile Computing and Networking, MobiCom 2020. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3372224.3419194","DOI":"10.1145\/3372224.3419194"},{"issue":"1","key":"21_CR21","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TWC.2019.2946140","volume":"19","author":"E Li","year":"2020","unstructured":"Li, E., Zeng, L., Zhou, Z., Chen, X.: Edge AI: on-demand accelerating deep neural network inference via edge computing. IEEE Trans. Wireless Commun. 19(1), 447\u2013457 (2020). https:\/\/doi.org\/10.1109\/TWC.2019.2946140","journal-title":"IEEE Trans. Wireless Commun."},{"issue":"7","key":"21_CR22","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1109\/TPDS.2020.3041474","volume":"32","author":"J Du","year":"2021","unstructured":"Du, J., et al.: Model parallelism optimization for distributed inference via decoupled CNN structure. IEEE Trans. Parallel Distrib. Syst. 32(7), 1665\u20131676 (2021). https:\/\/doi.org\/10.1109\/TPDS.2020.3041474","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"7","key":"21_CR23","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1109\/TPDS.2020.3043449","volume":"32","author":"K Zhao","year":"2021","unstructured":"Zhao, K., et al.: FT-CNN: algorithm-based fault tolerance for convolutional neural networks. IEEE Trans. Parallel Distrib. Syst. 32(7), 1677\u20131689 (2021). https:\/\/doi.org\/10.1109\/TPDS.2020.3043449","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"21_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Ma","year":"2018","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8"},{"key":"21_CR25","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient transfer learning. arXiv preprint arXiv:1611.06440 3 (2016)"},{"key":"21_CR26","unstructured":"Zhang, L., Tan, Z., Song, J., Chen, J., Bao, C., Ma, K.: SCAN: a scalable neural networks framework towards compact and efficient models. arXiv preprint arXiv:1906.03951 (2019)"},{"key":"21_CR27","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR28","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images, pp. 32\u201333 (2009). https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"key":"21_CR29","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95388-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T17:16:31Z","timestamp":1674839791000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95388-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030953874","9783030953881"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95388-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/ica3pp2021\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"403","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":"145","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":"0","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":"36% - 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":"3.12","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":"2.27","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}