{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T03:06:25Z","timestamp":1765422385832,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,4]]},"DOI":"10.1145\/3737899.3768527","type":"proceedings-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T17:01:43Z","timestamp":1764694903000},"page":"77-84","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["G\n                    <scp>ist<\/scp>\n                    - Optimizing Segmentation for Decentralized Federated Learning on Tiny Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2155-1288","authenticated-orcid":false,"given":"Navidreza","family":"Asadi","sequence":"first","affiliation":[{"name":"Technical University of Munich Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1863-5899","authenticated-orcid":false,"given":"Halil \u0130brahim","family":"Bengu","sequence":"additional","affiliation":[{"name":"Technical University of Munich Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0746-8717","authenticated-orcid":false,"given":"Lars","family":"Wulfert","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Microelectronic Circuits and Systems Duisburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5171-0756","authenticated-orcid":false,"given":"Hendrik","family":"W\u00f6hrle","sequence":"additional","affiliation":[{"name":"University of Duisburg-Essen Duisburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4358-8038","authenticated-orcid":false,"given":"Wolfgang","family":"Kellerer","sequence":"additional","affiliation":[{"name":"Technical University of Munich Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680207.3765668"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1109\/JIOT.2023.3285877","article-title":"Variant parallelism: lightweight deep convolutional models for distributed inference on IoT devices","volume":"11","author":"Asadi Navidreza","year":"2023","unstructured":"Navidreza Asadi and Maziar Goudarzi. 2023. Variant parallelism: lightweight deep convolutional models for distributed inference on IoT devices. IEEE Internet of Things Journal 11, 1 (2023), 345--352.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.927071"},{"key":"e_1_3_2_1_4_1","volume-title":"FREENIX Track","volume":"41","author":"Bellard Fabrice","year":"2005","unstructured":"Fabrice Bellard. 2005. QEMU, a fast and portable dynamic translator. In USENIX annual technical conference, FREENIX Track, Vol. 41. California, USA, 10--55."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3315746"},{"key":"e_1_3_2_1_6_1","volume-title":"PyTorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration. https:\/\/github.com\/pytorch\/pytorch. GitHub repository, version as of","author":"Chintala Soumith","year":"2025","unstructured":"Soumith Chintala, Gregory Chanan, Dmytro Dzhulgakov, Edward Yang, Nikita Shulga, and The PyTorch Team. 2025. PyTorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration. https:\/\/github.com\/pytorch\/pytorch. GitHub repository, version as of July 23, 2025."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"e_1_3_2_1_8_1","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861 [cs.CV] https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"e_1_3_2_1_9_1","unstructured":"Chenghao Hu Jingyan Jiang and Zhi Wang. 2019. Decentralized Federated Learning: A Segmented Gossip Approach. arXiv:1908.07782 [cs.LG] https:\/\/arxiv.org\/abs\/1908.07782"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2024.3370402"},{"key":"e_1_3_2_1_11_1","unstructured":"Anastasia Koloskova Sebastian U. Stich and Martin Jaggi. 2019. Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication. arXiv:1902.00340 [cs.LG] https:\/\/arxiv.org\/abs\/1902.00340"},{"key":"e_1_3_2_1_12_1","volume-title":"Ananda Theertha Suresh, and Dave Bacon","author":"Kone\u010dny Jakub","year":"2016","unstructured":"Jakub Kone\u010dny, H Brendan McMahan, Felix X Yu, Peter Richt\u00e1rik, Ananda Theertha Suresh, and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492 (2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"Ananda Theertha Suresh, and Dave Bacon","author":"Kone\u010dn\u00fd Jakub","year":"2017","unstructured":"Jakub Kone\u010dn\u00fd, H. Brendan McMahan, Felix X. Yu, Peter Richt\u00e1rik, Ananda Theertha Suresh, and Dave Bacon. 2017. Federated Learning: Strategies for Improving Communication Efficiency. arXiv:1610.05492 [cs.LG] https:\/\/arxiv.org\/abs\/1610.05492"},{"key":"e_1_3_2_1_14_1","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. (2009) 32--33. https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_16_1","unstructured":"Sunwoo Lee Tuo Zhang Chaoyang He and Salman Avestimehr. 2022. Layer-wise Adaptive Model Aggregation for Scalable Federated Learning. arXiv:2110.10302 [cs.LG] https:\/\/arxiv.org\/abs\/2110.10302"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2024.110663"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3329005"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 18th ACM international conference on Multimedia. 1485-1488","author":"Marcel S\u00e9bastien","year":"2010","unstructured":"S\u00e9bastien Marcel and Yann Rodriguez. 2010. Torchvision the machinevision package of torch. In Proceedings of the 18th ACM international conference on Multimedia. 1485-1488."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2023.3315746"},{"key":"e_1_3_2_1_21_1","unstructured":"H. Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Ag\u00fcera y Arcas. 2023. Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv:1602.05629 [cs.LG] https:\/\/arxiv.org\/abs\/1602.05629"},{"key":"e_1_3_2_1_22_1","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization. arXiv:1902.05967 [cs.LG] https:\/\/arxiv.org\/abs\/1902.05967"},{"key":"e_1_3_2_1_23_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"QEMU: A Generic and Open Source Machine Emulator and Virtualizer. https:\/\/www.qemu.org\/. Version 10.0.2, accessed","author":"Project QEMU","year":"2025","unstructured":"QEMU Project. 2025. QEMU: A Generic and Open Source Machine Emulator and Virtualizer. https:\/\/www.qemu.org\/. Version 10.0.2, accessed July 23, 2025."},{"key":"e_1_3_2_1_25_1","volume-title":"Federated learning for cyber physical systems: a comprehensive survey","author":"Quan Minh K","year":"2025","unstructured":"Minh K Quan, Pubudu N Pathirana, Mayuri Wijayasundara, Sujeeva Setunge, Dinh C Nguyen, Christopher G Brinton, David J Love, and H Vincent Poor. 2025. Federated learning for cyber physical systems: a comprehensive survey. IEEE Communications Surveys & Tutorials (2025)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196503"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3230938"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2022.3189051"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987586"},{"key":"e_1_3_2_1_30_1","volume-title":"FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction. arXiv:2407.19389 [cs.DC] https:\/\/arxiv.org\/abs\/2407.19389","author":"Wu Feijie","year":"2024","unstructured":"Feijie Wu, Xingchen Wang, Yaqing Wang, Tianci Liu, Lu Su, and Jing Gao. 2024. FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction. arXiv:2407.19389 [cs.DC] https:\/\/arxiv.org\/abs\/2407.19389"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630048.3630181"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355495"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625558"},{"key":"e_1_3_2_1_34_1","volume-title":"Brinton","author":"Yuan Liangqi","year":"2024","unstructured":"Liangqi Yuan, Ziran Wang, Lichao Sun, Philip S. Yu, and Christopher G. Brinton. 2024. Decentralized Federated Learning: A Survey and Perspective. arXiv:2306.01603 [cs.LG] https:\/\/arxiv.org\/abs\/2306.01603"}],"event":{"name":"ACM MobiCom '25: The 31st Annual International Conference on Mobile Computing and Networking","location":"Hong Kong China","acronym":"FLEdge-AI '25","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Federated Learning and Edge AI for Privacy and Mobility"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3737899.3768527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T17:02:11Z","timestamp":1764694931000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3737899.3768527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":34,"alternative-id":["10.1145\/3737899.3768527","10.1145\/3737899"],"URL":"https:\/\/doi.org\/10.1145\/3737899.3768527","relation":{},"subject":[],"published":{"date-parts":[[2025,11,4]]},"assertion":[{"value":"2025-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}