{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:18:44Z","timestamp":1757618324258,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819687275"},{"type":"electronic","value":"9789819687282"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-8728-2_3","type":"book-chapter","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T10:30:47Z","timestamp":1750588247000},"page":"25-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Latency-Optimal and\u00a0Memory-Aware Model Partitioning for\u00a0Cooperative Inference at\u00a0the\u00a0Edge"],"prefix":"10.1007","author":[{"given":"Quan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianglun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingshu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,21]]},"reference":[{"issue":"1","key":"3_CR1","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/COMST.2022.3218527","volume":"25","author":"S Duan","year":"2023","unstructured":"Duan, S., et al.: Distributed artificial intelligence empowered by end-edge-cloud computing: a survey. IEEE Commun. Surv. Tutor. 25(1), 591\u2013624 (2023)","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Banitalebi-Dehkordi, A., Vedula, N., Pei, J., et al.: Auto-split: a general framework of collaborative edge-cloud AI. In: Proceedings of the ACM SIGKDD, pp. 2543\u20132553 (2021)","DOI":"10.1145\/3447548.3467078"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Huang, Y., Qiao, X., Dustdar, S., et al.: AoDNN: an auto-offloading approach to optimize deep inference for fostering mobile web. In: Proceedings of the IEEE INFOCOM (2022)","DOI":"10.1109\/INFOCOM48880.2022.9796763"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Guo, S., Xu, W., et al.: Average AoI minimization with directional charging for wireless-powered network edge. IEEE Trans. Mob. Comput. (2025)","DOI":"10.1109\/TMC.2025.3527559"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Wang, C., Cai, Z., Li, Y.: Human activity recognition in mobile edge computing: a low-cost and high-fidelity digital twin approach with deep reinforcement learning. IEEE Trans. Consum. Electron. (2025)","DOI":"10.1109\/TCE.2024.3375859"},{"issue":"2","key":"3_CR6","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1109\/TNET.2022.3196267","volume":"31","author":"T Shi","year":"2023","unstructured":"Shi, T., et al.: Services management and distributed multi-hop requests routing in mobile edge networks. IEEE\/ACM Trans. Netw. 31(2), 497\u2013510 (2023)","journal-title":"IEEE\/ACM Trans. Netw."},{"issue":"16","key":"3_CR7","doi-asserted-by":"publisher","first-page":"12679","DOI":"10.1109\/JIOT.2020.3026988","volume":"8","author":"Z Cai","year":"2021","unstructured":"Cai, Z., Shi, T.: Distributed query processing in the edge assisted IoT data monitoring system. IEEE Internet Things J. 8(16), 12679\u201312693 (2021)","journal-title":"IEEE Internet Things J."},{"issue":"1","key":"3_CR8","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. ACM SIGARCH Comput. Archit. News 45(1), 615\u2013629 (2017)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Liang, H., Sang, Q. Hu, C., et al.: DNN surgery: accelerating DNN inference on the edge through layer partitioning. IEEE Trans. Cloud Comput. (2023)","DOI":"10.1109\/TCC.2023.3258982"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Y., Liu, X., et al.: Towards real-time cooperative deep inference over the cloud and edge end devices. In: Proceedings of the ACM Ubicomp, vol. 4, no. 2, pp. 1\u201324 (2020)","DOI":"10.1145\/3397315"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hu, C., Li, B.: Distributed inference with deep learning models across heterogeneous edge devices. In: Proceedings of the IEEE INFOCOM, London, UK, pp. 330\u2013333 (2022)","DOI":"10.1109\/INFOCOM48880.2022.9796896"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Liu, K., Liu, C., Yan, G., et al.: Accelerating DNN inference with reliability guarantee in vehicular edge computing. In: IEEE\/ACM Trans. Netw. (2023)","DOI":"10.1109\/TNET.2023.3279512"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Duan, Y., Wu, J.: Joint optimization of dnn partition and scheduling for mobile cloud computing. In: Proceedings of the International Conference on Parallel Processing, pp. 1\u201310 (2021)","DOI":"10.1145\/3472456.3472468"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Yang, X., Xu, Z., Qi, Q., et al.: PICO: pipeline inference framework for versatile CNNs on diverse mobile devices. IEEE Trans. Mob. Comput. (2024)","DOI":"10.1109\/TMC.2023.3265111"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Mohammed, T., Joe-Wong, C., Babbar, R., et al.: Distributed inference acceleration with adaptive DNN partitioning and offloading. In: Proceedings of the IEEE INFOCOM, pp. 854\u2013863 (2020)","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Yang, R., Li, Y., He, H., et al.: DNN real-time collaborative inference acceleration with mobile edge computing. In: International Joint Conference on Neural Networks (2022)","DOI":"10.1109\/IJCNN55064.2022.9892582"},{"issue":"2","key":"3_CR17","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/TMC.2019.2947893","volume":"20","author":"AE Eshratifar","year":"2021","unstructured":"Eshratifar, A.E., Abrishami, M.S., Pedram, M.: JointDNN: an efficient training and inference engine for intelligent mobile cloud computing services. IEEE Trans. Mob. Comput. 20(2), 565\u2013576 (2021)","journal-title":"IEEE Trans. Mob. Comput."},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Yan, J., Bi, S., Zhang, Y.-J.A.: Optimal model placement and online model splitting for device-edge co-inference. IEEE Trans. Wirel. Commun. (2022)","DOI":"10.1109\/TWC.2022.3165824"},{"issue":"8","key":"3_CR19","doi-asserted-by":"publisher","first-page":"5456","DOI":"10.1109\/TII.2019.2961237","volume":"16","author":"B Lin","year":"2019","unstructured":"Lin, B., et al.: Cost-driven off-loading for DNN-based applications over cloud, edge, and end devices. IEEE Trans. Industr. Inf. 16(8), 5456\u20135466 (2019)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Fan, W., et al.: Joint DNN partition and resource allocation for task offloading in edge-cloud-assisted IoT environments. IEEE Internet Things J. (2023)","DOI":"10.1109\/JIOT.2023.3237361"},{"issue":"12","key":"3_CR21","doi-asserted-by":"publisher","first-page":"13076","DOI":"10.1109\/TMC.2024.3430103","volume":"23","author":"Y Li","year":"2024","unstructured":"Li, Y., et al.: Real-time adaptive partition and resource allocation for multi-user end-cloud inference collaboration in mobile environment. IEEE Trans. Mob. Comput. 23(12), 13076\u201313094 (2024)","journal-title":"IEEE Trans. Mob. Comput."},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Li, A., Zeng, L., Zhou, Z., Chen, X.: Edge AI: on-demand accelerating deep neural network inference via edge computing. IEEE Trans. Wirel. Commun. (2019)","DOI":"10.1109\/TWC.2019.2946140"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Miao, W., Zeng, Z., Wei, L., et al.: Adaptive DNN partition in edge computing environments. In: Proceedings of the ICPADS (2020)","DOI":"10.1109\/ICPADS51040.2020.00097"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Context-aware adaptive surgery: a fast and effective framework for adaptative model partition. In: Proceedings of the ACM Ubicomp, vol. 5, no. 3, pp. 1\u201322 (2021)","DOI":"10.1145\/3478073"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Jeong, H., Lee, H., Shin, K., et al.: PerDNN: offloading deep neural network computations to pervasive edge servers. In: Proceedings of the IEEE ICDCS (2020)","DOI":"10.1109\/ICDCS47774.2020.00114"},{"issue":"2","key":"3_CR26","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TNET.2020.3042320","volume":"29","author":"L Zeng","year":"2021","unstructured":"Zeng, L., et al.: CoEdge: Cooperative DNN inference with adaptive workload partitioning over heterogeneous edge devices. IEEE\/ACM Trans. Netw. 29(2), 595\u2013608 (2021)","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Lim, J., Kim, Y.: Real-time DNN model partitioning for QoE enhancement in mobile vision applications. In: Proceedings of the IEEE SECON, Stockholm, Sweden, pp. 407\u2013415 (2022)","DOI":"10.1109\/SECON55815.2022.9918600"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3_CR29","unstructured":"Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, pp. 1877\u20131901 (2020)"},{"key":"3_CR30","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the NIPS (2012)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Chen, Q., et al.: Towards real-time inference offloading with distributed edge computing: the framework and algorithms. IEEE Trans. Mobile Comput. (2024)","DOI":"10.1109\/TMC.2023.3335051"},{"issue":"6","key":"3_CR32","doi-asserted-by":"publisher","first-page":"7335","DOI":"10.1109\/TMC.2023.3332668","volume":"23","author":"J Li","year":"2024","unstructured":"Li, J., et al.: Digital twin-enabled service provisioning in edge computing via continual learning. IEEE Trans. Mob. Comput. 23(6), 7335\u20137350 (2024)","journal-title":"IEEE Trans. Mob. Comput."},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Yuan, X., Li, N., Wei, K., et al.: Mobility and cost aware inference accelerating algorithm for edge intelligence. IEEE Trans. Mob. Comput. (2024)","DOI":"10.1109\/TMC.2024.3484158"},{"key":"3_CR34","unstructured":"torchinfo. https:\/\/github.com\/TylerYep\/torchinfo"},{"key":"3_CR35","unstructured":"MobileWiFi. https:\/\/www.zhe2.com\/note\/672744348840"}],"container-title":["Lecture Notes in Computer Science","Wireless Artificial Intelligent Computing Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8728-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T21:30:27Z","timestamp":1757194227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8728-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819687275","9789819687282"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8728-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"21 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Wireless Artificial Intelligent Computing Systems and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wasa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wasa-conference.org\/WASA2025\/index.html#","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}