{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:37:08Z","timestamp":1783438628856,"version":"3.54.6"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"SRC Global Research Collaboration","award":["GRC TASK 3021.001"],"award-info":[{"award-number":["GRC TASK 3021.001"]}]},{"name":"NSF","award":["#2112665, #2003279, #2120019, #2211386, #2052809, #1911095, and #2112167"],"award-info":[{"award-number":["#2112665, #2003279, #2120019, #2211386, #2052809, #1911095, and #2112167"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Things"],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:p>Federated learning is a distributed learning method by training the model in locally multiple clients, which has been used in numerous fields. Current convolutional neural networks (CNN)-based federated learning approaches face challenges from computational cost, communication efficiency, and robust communication. Recently, Hyper Dimensional Computing (HDC) has been recognized as a promising technique to address these challenges. HDC encodes data as high-dimensional vectors and enables lightweight training and communication through simple parallel vector operations. Several HDC-based federated learning methods have been proposed. Although existing methods reduce computational efficiency and communication cost, they are difficult to handle complex learning tasks and are not robust to unreliable wireless channels. In this work, we innovatively introduce a synergetic federated learning framework, FHDnn. With advantage of the complementary strengths of CNN and HDC, FHDnn can achieve optimal performance on complex image tasks while maintaining good computational and communication efficiency. Secondly, we demonstrate in detail the convergence of using HDC in a generalized federated learning framework, providing theoretical guarantees for HDC-based federated learning approach. Finally, we design three communication strategies to further improve the communication efficiency of FHDnn by 32\u00d7. Experiments demonstrate that FHDnn converges 3\u00d7 faster than CNN-based federated learning methods, reduces the communication cost by 2,112\u00d7, and the local computation and energy consumption by 192\u00d7. In addition, it has good robustness to unreliable communication with bit errors, noise, and packet loss.<\/jats:p>","DOI":"10.1145\/3724129","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T10:21:23Z","timestamp":1742293283000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Federated Hyperdimensional Computing: Comprehensive Analysis and Robust Communication"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8028-2532","authenticated-orcid":false,"given":"Ye","family":"Tian","sequence":"first","affiliation":[{"name":"University of California San Diego, La Jolla, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8738-8698","authenticated-orcid":false,"given":"Rishikanth","family":"Chandrasekaran","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5092-5074","authenticated-orcid":false,"given":"Kazim","family":"Ergun","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9638-6184","authenticated-orcid":false,"given":"Xiaofan","family":"Yu","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6954-997X","authenticated-orcid":false,"given":"Tajana","family":"Rosing","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Ron Cole Yeshwant Muthusamy and Mark Fanty. 1990. The ISOLET Spoken Letter Database. Oregon Graduate Institute of Science and Technology Department of Computer."},{"key":"e_1_3_2_3_2","unstructured":"Davide Anguita Alessandro Ghio Luca Oneto Xavier Parra and Jorge Luis Reyes-Ortiz. 2013. A public domain dataset for human activity recognition using smartphones. In Esann 3 (2013) 3\u20134."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154285"},{"key":"e_1_3_2_5_2","first-page":"560","volume-title":"International Conference on Machine Learning","author":"Bernstein Jeremy","year":"2018","unstructured":"Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, and Animashree Anandkumar. 2018. signSGD: Compressed optimisation for non-convex problems. In International Conference on Machine Learning. PMLR, 560\u2013569."},{"key":"e_1_3_2_6_2","article-title":"Expanding the reach of federated learning by reducing client resource requirements","author":"Caldas Sebastian","year":"2018","unstructured":"Sebastian Caldas, Jakub Kone\u010dny, H. Brendan McMahan, and Ameet Talwalkar. 2018. Expanding the reach of federated learning by reducing client resource requirements. arXiv preprint arXiv:1812.07210 (2018).","journal-title":"arXiv preprint arXiv:1812.07210"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530394"},{"key":"e_1_3_2_8_2","first-page":"1597","volume-title":"International Conference on Machine Learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning. PMLR, 1597\u20131607."},{"key":"e_1_3_2_9_2","article-title":"Optimal client sampling for federated learning","author":"Chen Wenlin","year":"2020","unstructured":"Wenlin Chen, Samuel Horvath, and Peter Richtarik. 2020. Optimal client sampling for federated learning. arXiv preprint arXiv:2010.13723 (2020).","journal-title":"arXiv preprint arXiv:2010.13723"},{"key":"e_1_3_2_10_2","unstructured":"NVIDIA Corporation. 2024. NVIDIA Jetson Nano. https:\/\/developer.nvidia.com\/embedded\/jetson-nano-developer-kit"},{"key":"e_1_3_2_11_2","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume":"28","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. BinaryConnect: Training deep neural networks with binary weights during propagations. Advances in Neural Information Processing Systems 28 (2015).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526241.3530331"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.80230"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2008.929967"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2020.2988388"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_20_2","article-title":"Natural compression for distributed deep learning","author":"Horv\u00e1th Samuel","year":"2019","unstructured":"Samuel Horv\u00e1th, Chen-Yu Ho, Ludovit Horvath, Atal Narayan Sahu, Marco Canini, and Peter Richt\u00e1rik. 2019. Natural compression for distributed deep learning. arXiv preprint arXiv:1905.10988 (2019).","journal-title":"arXiv preprint arXiv:1905.10988"},{"key":"e_1_3_2_21_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard Andrew G.","year":"2017","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 preprint arXiv:1704.04861 (2017).","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458526"},{"key":"e_1_3_2_23_2","unstructured":"Petroc Taylor. 2022. Data volume of IoT connected devices worldwide 2019 and 2025. https:\/\/www.statista.com\/statistics\/1017863\/worldwide-iot-connected-devices-data-size\/"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Mohsen Imani Justin Morris John Messerly Helen Shu Yaobang Deng and Tajana Rosing. 2019. Bric: Locality-based encoding for energy-efficient brain-inspired hyperdimensional computing. Proceedings of the 56th Annual Design Automation Conference 2019. 1\u20136.","DOI":"10.1145\/3316781.3317785"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00076"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2017.8123650"},{"key":"e_1_3_2_27_2","article-title":"Model pruning enables efficient federated learning on edge devices","author":"Jiang Yuang","year":"2022","unstructured":"Yuang Jiang, Shiqiang Wang, Victor Valls, Bong Jun Ko, Wei-Han Lee, Kin K. Leung, and Leandros Tassiulas. 2022. Model pruning enables efficient federated learning on edge devices. IEEE Transactions on Neural Networks and Learning Systems (2022).","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-009-9009-8"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the Annual Meeting of the Cognitive Science Society","volume":"22","author":"Kanerva Pentii","year":"2000","unstructured":"Pentii Kanerva, Jan Kristoferson, and Anders Holst. 2000. Random indexing of text samples for latent semantic analysis. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 22."},{"key":"e_1_3_2_30_2","first-page":"5132","volume-title":"International Conference on Machine Learning","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. 2020. Scaffold: Stochastic controlled averaging for federated learning. In International Conference on Machine Learning. PMLR, 5132\u20135143."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom60117.2023.00049"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530669"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3277593.3277617"},{"key":"e_1_3_2_34_2","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Kone\u010dn\u1ef3 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef3, H. Brendan McMahan, Daniel Ramage, and Peter Richt\u00e1rik. 2016. Federated optimization: Distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527 (2016).","journal-title":"arXiv preprint arXiv:1610.02527"},{"key":"e_1_3_2_35_2","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u1ef3 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef3, 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).","journal-title":"arXiv preprint arXiv:1610.05492"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2018.00062"},{"key":"e_1_3_2_37_2","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto. https:\/\/www.cs.utoronto.ca\/kriz\/learning-features-2009-TR.pdf"},{"key":"e_1_3_2_38_2","volume-title":"Computer Networking: A Top-down Approach Featuring the Internet, 3\/E","author":"Kurose James F.","year":"2005","unstructured":"James F. Kurose. 2005. Computer Networking: A Top-down Approach Featuring the Internet, 3\/E. Pearson Education India."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Fei-Fei Li Marco Andreeto Marc\u2019Aurelio Ranzato and Pietro Perona. 2022. Caltech 101. 10.22002\/D1.20086","DOI":"10.22002\/D1.20086"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473907"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106854"},{"key":"e_1_3_2_43_2","unstructured":"Xiang Li Kaixuan Huang Wenhao Yang Shusen Wang and Zhihua Zhang. 2019. On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189 (2019)."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196120"},{"key":"e_1_3_2_45_2","volume-title":"Artificial Intelligence and Statistics","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan et\u00a0al. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics."},{"key":"e_1_3_2_46_2","article-title":"Scalable model compression by entropy penalized reparameterization","author":"Oktay Deniz","year":"2019","unstructured":"Deniz Oktay, Johannes Ball\u00e9, Saurabh Singh, and Abhinav Shrivastava. 2019. Scalable model compression by entropy penalized reparameterization. arXiv preprint arXiv:1906.06624 (2019).","journal-title":"arXiv preprint arXiv:1906.06624"},{"key":"e_1_3_2_47_2","unstructured":"Raspberry Pi Foundation. 2024. Raspberry Pi 4 Model B. https:\/\/www.raspberrypi.com\/products\/raspberry-pi-4-model-b\/"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2871163"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934624"},{"key":"e_1_3_2_50_2","first-page":"2021","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Reisizadeh Amirhossein","year":"2020","unstructured":"Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, and Ramtin Pedarsani. 2020. FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization. In International Conference on Artificial Intelligence and Statistics. PMLR, 2021\u20132031."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892007"},{"key":"e_1_3_2_52_2","article-title":"Local SGD converges fast and communicates little","author":"Stich Sebastian U.","year":"2018","unstructured":"Sebastian U. Stich. 2018. Local SGD converges fast and communicates little. arXiv preprint arXiv:1805.09767 (2018).","journal-title":"arXiv preprint arXiv:1805.09767"},{"key":"e_1_3_2_53_2","first-page":"3329","volume-title":"International Conference on Machine Learning","author":"Suresh Ananda Theertha","year":"2017","unstructured":"Ananda Theertha Suresh, X. Yu Felix, Sanjiv Kumar, and H. Brendan McMahan. 2017. Distributed mean estimation with limited communication. In International Conference on Machine Learning. PMLR, 3329\u20133337."},{"key":"e_1_3_2_54_2","article-title":"SplitFed: When federated learning meets split learning","author":"Thapa Chandra","year":"2020","unstructured":"Chandra Thapa, Mahawaga Arachchige Pathum Chamikara, Seyit Camtepe, and Lichao Sun. 2020. SplitFed: When federated learning meets split learning. arXiv preprint arXiv:2004.12088 (2020).","journal-title":"arXiv preprint arXiv:2004.12088"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12664"},{"key":"e_1_3_2_56_2","article-title":"ProgFed: Effective, communication, and computation efficient federated learning by progressive training","author":"Wang Hui-Po","year":"2021","unstructured":"Hui-Po Wang, Sebastian U. Stich, Yang He, and Mario Fritz. 2021. ProgFed: Effective, communication, and computation efficient federated learning by progressive training. arXiv preprint arXiv:2110.05323 (2021).","journal-title":"arXiv preprint arXiv:2110.05323"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/79.855913"},{"key":"e_1_3_2_58_2","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume":"31","author":"Wangni Jianqiao","year":"2018","unstructured":"Jianqiao Wangni, Jialei Wang, Ji Liu, and Tong Zhang. 2018. Gradient sparsification for communication-efficient distributed optimization. Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3140788"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01647-y"},{"key":"e_1_3_2_61_2","volume-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao Han","year":"2017","unstructured":"Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:cs.LG\/1708.07747 [cs.LG]"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586241"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01585-4_4"},{"key":"e_1_3_2_64_2","article-title":"Resource-efficient federated hyperdimensional computing","author":"Zeulin Nikita","year":"2023","unstructured":"Nikita Zeulin, Olga Galinina, Nageen Himayat, and Sergey Andreev. 2023. Resource-efficient federated hyperdimensional computing. arXiv preprint arXiv:2306.01339 (2023).","journal-title":"arXiv preprint arXiv:2306.01339"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3558757"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546794"},{"key":"e_1_3_2_67_2","first-page":"312","volume-title":"Proceedings of the 22nd International Conference on Information Processing in Sensor Networks","author":"Zhao Quanling","year":"2023","unstructured":"Quanling Zhao, Xiaofan Yu, and Tajana Rosing. 2023. Attentive multimodal learning on sensor data using hyperdimensional computing. In Proceedings of the 22nd International Conference on Information Processing in Sensor Networks. 312\u2013313."},{"key":"e_1_3_2_68_2","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu Michael","year":"2017","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: Exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017).","journal-title":"arXiv preprint arXiv:1710.01878"}],"container-title":["ACM Transactions on Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3724129","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3724129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:59Z","timestamp":1750295939000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3724129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,29]]},"references-count":67,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,8,31]]}},"alternative-id":["10.1145\/3724129"],"URL":"https:\/\/doi.org\/10.1145\/3724129","relation":{},"ISSN":["2691-1914","2577-6207"],"issn-type":[{"value":"2691-1914","type":"print"},{"value":"2577-6207","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,29]]},"assertion":[{"value":"2024-08-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}