{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:54:32Z","timestamp":1776930872486,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":82,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Department of Energy","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767397","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"516-523","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8314-4745","authenticated-orcid":false,"given":"Sahil","family":"Tyagi","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3670-0813","authenticated-orcid":false,"given":"Andrei","family":"Cozma","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1677-2243","authenticated-orcid":false,"given":"Olivera","family":"Kotevska","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0099-1559","authenticated-orcid":false,"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2025. CIFAR10 and CIFAR100. https:\/\/www.cs.toronto.edu\/\u00a0kriz\/cifar.html"},{"key":"e_1_3_3_2_3_2","volume-title":"USENIX Symposium on Operating Systems Design and Implementation","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Z. Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek\u00a0Gordon Murray, Benoit Steiner, Paul\u00a0A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zhang. 2016. TensorFlow: A system for large-scale machine learning. In USENIX Symposium on Operating Systems Design and Implementation."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Mart\u00edn Abadi Andy Chu Ian\u00a0J. Goodfellow H.\u00a0B. McMahan Ilya Mironov Kunal Talwar and Li Zhang. 2016. Deep Learning with Differential Privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (2016).","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_3_2_5_2","unstructured":"Ahmed\u00a0Mohamed Abdelmoniem Ahmed Elzanaty Mohamed-Slim Alouini and Marco Canini. 2021. An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems. ArXiv abs\/2101.10761 (2021)."},{"key":"e_1_3_3_2_6_2","unstructured":"Durmus Alp\u00a0Emre Acar Yue Zhao Ramon\u00a0Matas Navarro Matthew Mattina Paul\u00a0N. Whatmough and Venkatesh Saligrama. 2021. Federated Learning Based on Dynamic Regularization. ArXiv abs\/2111.04263 (2021)."},{"key":"e_1_3_3_2_7_2","volume-title":"Neural Information Processing Systems","author":"Alistarh Dan","year":"2016","unstructured":"Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, and Milan Vojnovic. 2016. QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding. In Neural Information Processing Systems."},{"key":"e_1_3_3_2_8_2","unstructured":"Inc. Anyscale. [n. d.]. Ray: A Fast and Simple Framework for Distributed Computing. https:\/\/www.ray.io\/. Accessed: 2023-10-18."},{"key":"e_1_3_3_2_9_2","unstructured":"Manoj\u00a0Ghuhan Arivazhagan V. Aggarwal Aaditya\u00a0Kumar Singh and Sunav Choudhary. 2019. Federated Learning with Personalization Layers. ArXiv abs\/1912.00818 (2019)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Roopkatha Banerjee Prince Modi Jinal Vyas Chunduru\u00a0Sri Abhijit Tejus Chandrashekar Harsha\u00a0Varun Marisetty Manik Gupta and Yogesh\u00a0L. Simmhan. 2025. Flotilla: A scalable modular and resilient federated learning framework for heterogeneous resources. J. Parallel Distributed Comput. 203 (2025) 105103.","DOI":"10.1016\/j.jpdc.2025.105103"},{"key":"e_1_3_3_2_11_2","unstructured":"Ayoub Benaissa Bilal Retiat Bogdan Cebere and Alaa\u00a0Eddine Belfedhal. 2021. TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption. ArXiv abs\/2104.03152 (2021)."},{"key":"e_1_3_3_2_12_2","unstructured":"Daniel\u00a0J. Beutel Taner Topal Akhil Mathur Xinchi Qiu Titouan Parcollet and Nicholas\u00a0D. Lane. 2020. Flower: A Friendly Federated Learning Research Framework."},{"key":"e_1_3_3_2_13_2","unstructured":"Keith Bonawitz Hubert Eichner Wolfgang Grieskamp Dzmitry Huba Alex Ingerman Vladimir Ivanov Chlo\u00e9 Kiddon Jakub Konecn\u00fd Stefano Mazzocchi H.\u00a0B. McMahan Timon\u00a0Van Overveldt David Petrou Daniel Ramage and Jason Roselander. 2019. Towards Federated Learning at Scale: System Design. ArXiv abs\/1902.01046 (2019)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Keith Bonawitz Vladimir Ivanov Ben Kreuter Antonio Marcedone H.\u00a0B. McMahan Sarvar Patel Daniel Ramage Aaron Segal and Karn Seth. 2017. Practical Secure Aggregation for Privacy-Preserving Machine Learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (2017).","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Wes Brewer Matthias Maiterth Vineet Kumar Rafal\u00a0P. Wojda Sedrick Bouknight Jesse Hines Woong Shin Scott Greenwood David Grant Wesley Williams and Feiyi Wang. 2024. A Digital Twin Framework for Liquid-cooled Supercomputers as Demonstrated at Exascale. SC24: International Conference for High Performance Computing Networking Storage and Analysis (2024) 1\u201318.","DOI":"10.1109\/SC41406.2024.00029"},{"key":"e_1_3_3_2_16_2","unstructured":"Paris Carbone Asterios Katsifodimos Stephan Ewen Volker Markl Seif Haridi and Kostas Tzoumas. 2015. Apache Flink : Stream and batch processing in a single engine. IEEE Data(base) Engineering Bulletin 36 (2015) 28\u201333. https:\/\/api.semanticscholar.org\/CorpusID:263802939"},{"key":"e_1_3_3_2_17_2","unstructured":"Manuel\u00a0Jorge Cardoso Wenqi Li Richard Brown Nic Ma Eric Kerfoot Yiheng Wang Benjamin Murrey Andriy Myronenko and Can\u00a0Zhao et al.2022. MONAI: An open-source framework for deep learning in healthcare. ArXiv abs\/2211.02701 (2022)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Ryan Chard Y. Babuji Zhuozhao Li Tyler\u00a0J. Skluzacek Anna Woodard Ben Blaiszik Ian\u00a0T Foster and Kyle Chard. 2020. funcX: A Federated Function Serving Fabric for Science. Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing (2020).","DOI":"10.1145\/3369583.3392683"},{"key":"e_1_3_3_2_19_2","volume-title":"Financial Cryptography Workshops","author":"Chen Hao","year":"2016","unstructured":"Hao Chen, Kim Laine, and Rachel Player. 2016. Simple Encrypted Arithmetic Library - SEAL v2.1. In Financial Cryptography Workshops."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Muthu Dayalan. 2008. MapReduce: simplified data processing on large clusters. Commun. ACM 51 (2008) 107\u2013113.","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Whitfield Diffie and Martin\u00a0E. Hellman. 1976. New Directions in Cryptography. Democratizing Cryptography (1976).","DOI":"10.1109\/TIT.1976.1055638"},{"key":"e_1_3_3_2_22_2","unstructured":"Arthur Douillard Qixuang Feng Andrei\u00a0A. Rusu Rachita Chhaparia Yani Donchev Adhiguna Kuncoro Marc\u2019Aurelio Ranzato Arthur Szlam and Jiajun Shen. 2023. DiLoCo: Distributed Low-Communication Training of Language Models. ArXiv abs\/2311.08105 (2023)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Cynthia Dwork and Aaron Roth. 2014. The Algorithmic Foundations of Differential Privacy. Found. Trends Theor. Comput. Sci. 9 (2014) 211\u2013407.","DOI":"10.1561\/0400000042"},{"key":"e_1_3_3_2_24_2","unstructured":"Inc. Facebook. 2023. Gloo: Collective Communications Library. https:\/\/github.com\/facebookincubator\/gloo. Accessed: 2023-10-30."},{"key":"e_1_3_3_2_25_2","unstructured":"Jiarui Fang Haohuan Fu Guangwen Yang and Cho-Jui Hsieh. 2018. RedSync : Reducing Synchronization Traffic for Distributed Deep Learning. ArXiv abs\/1808.04357 (2018)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Li Fei-Fei Rob Fergus and Pietro Perona. 2006. One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (2006) 594\u2013611.","DOI":"10.1109\/TPAMI.2006.79"},{"key":"e_1_3_3_2_27_2","unstructured":"Apache\u00a0Software Foundation. 2022. Apache Kafka. https:\/\/kafka.apache.org\/. Version 3.2.0."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536440"},{"key":"e_1_3_3_2_29_2","unstructured":"Google. 2008. Protocol Buffers: Google\u2019s Data Interchange Format. Github. https:\/\/github.com\/protocolbuffers\/protobuf"},{"key":"e_1_3_3_2_30_2","unstructured":"Google. 2015. gRPC: A high-performance open-source universal RPC framework. https:\/\/grpc.io\/"},{"key":"e_1_3_3_2_31_2","unstructured":"Filip Granqvist Congzheng Song \u00c1ine Cahill Rogier van Dalen Martin Pelikan Yi\u00a0Sheng Chan Xiaojun Feng Natarajan Krishnaswami Vojta Jina and Mona Chitnis. 2024. pfl-research: simulation framework for accelerating research in Private Federated Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.06430 (2024)."},{"key":"e_1_3_3_2_32_2","unstructured":"Tom Gunter Zirui Wang Chong Wang Ruoming Pang Andy Narayanan Aonan Zhang and Bowen\u00a0Zhang et al.2025. Apple Intelligence Foundation Language Models. ArXiv abs\/2407.21075 (2025)."},{"key":"e_1_3_3_2_33_2","unstructured":"Chaoyang He Songze Li Jinhyun So Mi Zhang Hongyi Wang Xiaoyang Wang Praneeth Vepakomma Abhishek Singh Hang Qiu Li Shen Peilin Zhao Yan Kang Yang Liu Ramesh Raskar Qiang Yang Murali Annavaram and Salman Avestimehr. 2020. FedML: A Research Library and Benchmark for Federated Machine Learning. ArXiv abs\/2007.13518 (2020)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Kaiming He X. Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015) 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Andrew\u00a0G. Howard Mark Sandler Grace Chu Liang-Chieh Chen Bo Chen Mingxing Tan Weijun Wang Yukun Zhu Ruoming Pang Vijay Vasudevan Quoc\u00a0V. Le and Hartwig Adam. 2019. Searching for MobileNetV3. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019) 1314\u20131324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Urs Hunkeler Hong\u00a0Linh Truong and Andy\u00a0J. Stanford-Clark. 2008. MQTT-S \u2014 A publish\/subscribe protocol for Wireless Sensor Networks. 2008 3rd International Conference on Communication Systems Software and Middleware and Workshops (COMSWARE \u201908) (2008) 791\u2013798.","DOI":"10.1109\/COMSWA.2008.4554519"},{"key":"e_1_3_3_2_37_2","unstructured":"Zhouyuan Huo Qian Yang Bin Gu Lawrence Carin and Heng Huang. 2020. Faster On-Device Training Using New Federated Momentum Algorithm. ArXiv abs\/2002.02090 (2020)."},{"key":"e_1_3_3_2_38_2","unstructured":"An Ji Bortik Bandyopadhyay Congzheng Song Natarajan Krishnaswami Prabal Vashisht Rigel Smiroldo Isabel Litton Sayantan Mahinder Mona Chitnis and Andrew\u00a0W Hill. 2025. Private Federated Learning In Real World Application - A Case Study. ArXiv abs\/2502.04565 (2025)."},{"key":"e_1_3_3_2_39_2","volume-title":"International Conference on Machine Learning","author":"Karimireddy Sai\u00a0Praneeth","year":"2019","unstructured":"Sai\u00a0Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank\u00a0J. Reddi, Sebastian\u00a0U. Stich, and Ananda\u00a0Theertha Suresh. 2019. SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. In International Conference on Machine Learning."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. Commun. ACM 60 (2012) 84 \u2013 90.","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_2_41_2","unstructured":"Kubernetes 2025. Kubernetes Official Documentation. https:\/\/kubernetes.io\/docs\/. [Online; accessed 08-Aug-2025]."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Qinbin Li Bingsheng He and Dawn\u00a0Xiaodong Song. 2021. Model-Contrastive Federated Learning. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021) 10708\u201310717.","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"e_1_3_3_2_43_2","volume-title":"International Conference on Machine Learning","author":"Li Tian","year":"2020","unstructured":"Tian Li, Shengyuan Hu, Ahmad Beirami, and Virginia Smith. 2020. Ditto: Fair and Robust Federated Learning Through Personalization. In International Conference on Machine Learning."},{"key":"e_1_3_3_2_44_2","unstructured":"Xiaoxiao Li Meirui Jiang Xiaofei Zhang Michael Kamp and Qi Dou. 2021. FedBN: Federated Learning on Non-IID Features via Local Batch Normalization. ArXiv abs\/2102.07623 (2021)."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Zilinghan Li Shilan He Ze Yang Minseok Ryu Kibaek Kim and Ravi Madduri. 2024. Advances in Appfl: a Comprehensive and Extensible Federated Learning Framework. 2025 IEEE 25th International Symposium on Cluster Cloud and Internet Computing (CCGrid) (2024) 01\u201311.","DOI":"10.1109\/CCGRID64434.2025.00031"},{"key":"e_1_3_3_2_46_2","unstructured":"Wanchao Liang Tianyu Liu Less Wright Will Constable Andrew Gu Chien-Chin Huang Iris Zhang Wei Feng Howard Huang Junjie Wang Sanket Purandare Gokul Nadathur and Stratos Idreos. 2024. TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training. ArXiv abs\/2410.06511 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273228883"},{"key":"e_1_3_3_2_47_2","unstructured":"Yujun Lin Song Han Huizi Mao Yu Wang and William\u00a0J. Dally. 2017. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. ArXiv abs\/1712.01887 (2017)."},{"key":"e_1_3_3_2_48_2","unstructured":"Yang Liu Tao Fan Tianjian Chen Qian Xu and Qiang Yang. 2021. FATE: An Industrial Grade Platform for Collaborative Learning With Data Protection. J. Mach. Learn. Res. 22 (2021) 226:1\u2013226:6."},{"key":"e_1_3_3_2_49_2","volume-title":"International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_50_2","unstructured":"Heiko Ludwig Nathalie Baracaldo Gegi Thomas Yi Zhou Ali Anwar Shashank Rajamoni Yuya Ong Jayaram Radhakrishnan Ashish Verma Mathieu Sinn et\u00a0al. 2020. IBM Federated Learning: an Enterprise Framework White Paper V0. 1. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2007.10987 (2020)."},{"key":"e_1_3_3_2_51_2","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"McMahan H.\u00a0B.","year":"2016","unstructured":"H.\u00a0B. McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise\u00a0Ag\u00fcera y Arcas. 2016. Communication-Efficient Learning of Deep Networks from Decentralized Data. In International Conference on Artificial Intelligence and Statistics."},{"key":"e_1_3_3_2_52_2","unstructured":"Dirk Merkel. 2014. Docker: lightweight linux containers for consistent development and deployment. Linux journal 2014 239 (2014) 2."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Alfonso Monaco Ester Pantaleo Nicola Amoroso Antonio Lacalamita Claudio\u00a0Lo Giudice Adriano Fonzino Bruno Fosso Ernesto Picardi Sabina\u00a0Sonia Tangaro Graziano Pesole and Roberto Bellotti. 2021. A primer on machine learning techniques for genomic applications. Computational and Structural Biotechnology Journal 19 (2021) 4345 \u2013 4359.","DOI":"10.1016\/j.csbj.2021.07.021"},{"key":"e_1_3_3_2_54_2","unstructured":"Philipp Moritz Robert Nishihara Stephanie Wang Alexey Tumanov Richard Liaw Eric Liang William Paul Michael\u00a0I. Jordan and Ion Stoica. 2017. Ray: A Distributed Framework for Emerging AI Applications. ArXiv abs\/1712.05889 (2017)."},{"key":"e_1_3_3_2_55_2","unstructured":"NVIDIA. 2023. NCCL: NVIDIA Collective Communications Library. https:\/\/github.com\/NVIDIA\/nccl. Accessed: 2023-10-30."},{"key":"e_1_3_3_2_56_2","unstructured":"ORNL. 2025. PETINA: Privacy prEservaTIoN Algorithms. Github. https:\/\/github.com\/ORNL\/PETINA"},{"key":"e_1_3_3_2_57_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan and Trevor\u00a0Killeen et al.2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. ArXiv abs\/1912.01703 (2019)."},{"key":"e_1_3_3_2_58_2","volume-title":"hashlib \u2014 Secure hashes and message digests","author":"Foundation Python Software","year":"2023","unstructured":"Python Software Foundation. 2023. hashlib \u2014 Secure hashes and message digests. https:\/\/docs.python.org\/3\/library\/hashlib.html Accessed: 2023-10-12."},{"key":"e_1_3_3_2_59_2","volume-title":"hmac \u2014 Keyed-Hashing for Message Authentication","author":"Foundation Python Software","year":"2023","unstructured":"Python Software Foundation. 2023. hmac \u2014 Keyed-Hashing for Message Authentication. https:\/\/docs.python.org\/3\/library\/hmac.html Accessed: 2023-10-12."},{"key":"e_1_3_3_2_60_2","unstructured":"PyTorch. 2025. ExecuTorch: On-Device AI for Mobile and Embedded via PyTorch. https:\/\/github.com\/pytorch\/executorch. v0.7.0-release."},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","unstructured":"Jeff Rasley Samyam Rajbhandari Olatunji Ruwase and Yuxiong He. 2020. DeepSpeed: System Optimizations Enable Training Deep Learning Models with Over 100 Billion Parameters(KDD \u201920). Association for Computing Machinery New York NY USA 3505\u20133506. 10.1145\/3394486.3406703","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"crossref","unstructured":"G.\u00a0Anthony Reina Alexey Gruzdev Patrick Foley Olga\u00a0S. Perepelkina Mansi Sharma Igor Davidyuk Ilya Trushkin Maksim Radionov Aleksandr Mokrov Dmitry Agapov Jason Martin Brandon Edwards Micah\u00a0J. Sheller Sarthak Pati Prakash\u00a0Narayana Moorthy Shih-Han Wang Prashant Shah and Spyridon Bakas. 2021. OpenFL: the open federated learning library. Physics in Medicine and Biology 67 (2021).","DOI":"10.1088\/1361-6560\/ac97d9"},{"key":"e_1_3_3_2_63_2","unstructured":"Holger\u00a0R. Roth Yan Cheng Yuhong Wen Isaac Yang Ziyue Xu Yuan-Ting Hsieh Kristopher Kersten Ahmed\u00a0El Harouni Can Zhao Kevin Lu Zhihong Zhang Wenqi Li Andriy Myronenko Dong Yang Sean\u00a0Bin Yang Nicola Rieke Abood Quraini Chester Chen Daguang Xu Nic Ma Prerna Dogra Mona\u00a0G. Flores and Andrew Feng. 2022. NVIDIA FLARE: Federated Learning from Simulation to Real-World. ArXiv abs\/2210.13291 (2022)."},{"key":"e_1_3_3_2_64_2","unstructured":"Minseok Ryu Youngdae Kim Kibaek Kim and Ravi Madduri. 2022. APPFL: Open-Source Software Framework for Privacy-Preserving Federated Learning. 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (2022) 1074\u20131083."},{"key":"e_1_3_3_2_65_2","unstructured":"Anit\u00a0Kumar Sahu Tian Li Maziar Sanjabi Manzil Zaheer Ameet Talwalkar and Virginia Smith. 2018. Federated Optimization in Heterogeneous Networks. arXiv:https:\/\/arXiv.org\/abs\/Learning (2018)."},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"crossref","unstructured":"Anjana\u00a0M. Samarakoon David\u00a0Alan Tennant Feng Ye Qiang Zhang and Santiago\u00a0A. Grigera. 2022. Integration of machine learning with neutron scattering for the Hamiltonian tuning of spin ice under pressure. Communications Materials 3 (2022).","DOI":"10.1038\/s43246-022-00306-7"},{"key":"e_1_3_3_2_67_2","unstructured":"Alexander Sergeev and Mike\u00a0Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. ArXiv abs\/1802.05799 (2018)."},{"key":"e_1_3_3_2_68_2","unstructured":"Shaohuai Shi Xiaowen Chu Ka\u00a0Chun Cheung and S. See. 2019. Understanding Top-k Sparsification in Distributed Deep Learning. ArXiv abs\/1911.08772 (2019)."},{"key":"e_1_3_3_2_69_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014)."},{"key":"e_1_3_3_2_70_2","unstructured":"The MPICH\u00a0Development Team. 2023. MPICH: High-Performance and Widely Portable MPI. https:\/\/www.mpich.org. Accessed: 2023-10-30."},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"crossref","unstructured":"Rajeev Thakur Rolf Rabenseifner and William Gropp. 2005. Optimization of Collective Communication Operations in MPICH. The International Journal of High Performance Computing Applications 19 (2005) 49 \u2013 66.","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_3_2_72_2","unstructured":"Sahil Tyagi. 2025. An Overview of Computational and Communication Mechanisms for Scalable AI Systems. https:\/\/www.researchgate.net\/publication\/390663625_An_Overview_of_Computational_and_Communication_Mechanisms_for_Scalable_AI_Systems. Unpublished manuscript."},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Sahil Tyagi and Prateek Sharma. 2020. Taming Resource Heterogeneity In Distributed ML Training With Dynamic Batching. 2020 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) (2020) 188\u2013194.","DOI":"10.1109\/ACSOS49614.2020.00041"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"crossref","unstructured":"Sahil Tyagi and Prateek Sharma. 2025. OmniLearn: A Framework for Distributed Deep Learning Over Heterogeneous Clusters. IEEE Transactions on Parallel and Distributed Systems 36 (2025) 1253\u20131267.","DOI":"10.1109\/TPDS.2025.3553066"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Sahil Tyagi and Martin Swany. 2022. ScaDLES: Scalable Deep Learning over Streaming data at the Edge. 2022 IEEE International Conference on Big Data (Big Data) (2022) 2113\u20132122.","DOI":"10.1109\/BigData55660.2022.10020597"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"crossref","unstructured":"Sahil Tyagi and Martin Swany. 2023. GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training. 2023 IEEE 16th International Conference on Cloud Computing (CLOUD) (2023) 319\u2013329.","DOI":"10.1109\/CLOUD60044.2023.00045"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Steve Vinoski. 2006. Advanced Message Queuing Protocol. IEEE Internet Computing 10 (2006).","DOI":"10.1109\/MIC.2006.116"},{"key":"e_1_3_3_2_78_2","unstructured":"Thijs Vogels Sai\u00a0Praneeth Karimireddy and Martin Jaggi. 2019. PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization. ArXiv abs\/1905.13727 (2019)."},{"key":"e_1_3_3_2_79_2","unstructured":"Jianyu Wang Qinghua Liu Hao Liang Gauri Joshi and H.\u00a0Vincent Poor. 2020. Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization. ArXiv abs\/2007.07481 (2020)."},{"key":"e_1_3_3_2_80_2","unstructured":"Omry Yadan. 2019. Hydra - A framework for elegantly configuring complex applications. Github. https:\/\/github.com\/facebookresearch\/hydra"},{"key":"e_1_3_3_2_81_2","unstructured":"Omry Yadan. 2019. OmegaConf. Github. https:\/\/github.com\/omry\/omegaconf"},{"key":"e_1_3_3_2_82_2","volume-title":"Symposium on Networked Systems Design and Implementation","author":"Zaharia Matei\u00a0A.","year":"2012","unstructured":"Matei\u00a0A. Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauly, Michael\u00a0J. Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing. In Symposium on Networked Systems Design and Implementation."},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Alexander Ziller Andrew Trask Antonio Lopardo Benjamin Szymkow Bobby Wagner Emma Bluemke Jean-Mickael Nounahon Jonathan Passerat-Palmbach Kritika Prakash Nick Rose Th\u00e9o Ryffel Zarreen\u00a0Naowal Reza and Georgios Kaissis. 2021. PySyft: A Library for Easy Federated Learning.","DOI":"10.1007\/978-3-030-70604-3_5"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3731599.3767397","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767397","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:34:51Z","timestamp":1767987291000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767397"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":82,"alternative-id":["10.1145\/3731599.3767397","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767397","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}