{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T17:59:15Z","timestamp":1772819955098,"version":"3.50.1"},"reference-count":68,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T00:00:00Z","timestamp":1725840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>Recent advancements in neuroimaging have led to greater data sharing among the scientific community. However, institutions frequently maintain control over their data, citing concerns related to research culture, privacy, and accountability. This creates a demand for innovative tools capable of analyzing amalgamated datasets without the need to transfer actual data between entities. To address this challenge, we propose a decentralized sparse federated learning (FL) strategy. This approach emphasizes local training of sparse models to facilitate efficient communication within such frameworks. By capitalizing on model sparsity and selectively sharing parameters between client sites during the training phase, our method significantly lowers communication overheads. This advantage becomes increasingly pronounced when dealing with larger models and accommodating the diverse resource capabilities of various sites. We demonstrate the effectiveness of our approach through the application to the Adolescent Brain Cognitive Development (ABCD) dataset.<\/jats:p>","DOI":"10.3389\/fninf.2024.1430987","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T00:43:36Z","timestamp":1725842616000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Efficient federated learning for distributed neuroimaging data"],"prefix":"10.3389","volume":"18","author":[{"given":"Bishal","family":"Thapaliya","sequence":"first","affiliation":[]},{"given":"Riyasat","family":"Ohib","sequence":"additional","affiliation":[]},{"given":"Eloy","family":"Geenjaar","sequence":"additional","affiliation":[]},{"given":"Jingyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Vince","family":"Calhoun","sequence":"additional","affiliation":[]},{"given":"Sergey M.","family":"Plis","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1145\/2976749.2978318","article-title":"\u201cDeep learning with differential privacy,\u201d","volume-title":"Proceedings of the 2016 ACM SIGSAC conference on computer and communications security","author":"Abadi","year":"2016"},{"key":"B2","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/s41467-020-20655-6","article-title":"Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning","volume":"12","author":"Abrol","year":"2021","journal-title":"Nat. Commun"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.15579","article-title":"Single-shot pruning for offline reinforcement learning","author":"Arnob","year":"2021","journal-title":"arXiv"},{"key":"B4","doi-asserted-by":"publisher","first-page":"6080","DOI":"10.1609\/aaai.v36i6.20555","article-title":"Federated dynamic sparse training: computing less, communicating less, yet learning better","volume":"36","author":"Bibikar","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B5","doi-asserted-by":"publisher","first-page":"374","DOI":"10.48550\/arXiv.1902.01046","article-title":"Towards federated learning at scale: system design","volume":"1","author":"Bonawitz","year":"2019","journal-title":"Proc. Mach. Learn. Syst"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1145\/3133956.3133982","article-title":"\u201cPractical secure aggregation for privacy-preserving machine learning,\u201d","volume-title":"Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security","author":"Bonawitz","year":"2017"},{"key":"B7","unstructured":"Wafer Scale Engine: Why We Need Big Chips for Deep Learning2019"},{"key":"B8","doi-asserted-by":"publisher","first-page":"15834","DOI":"10.48550\/arXiv.2007.12223","article-title":"The lottery ticket hypothesis for pre-trained bert networks","volume":"33","author":"Chen","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2108.07313","article-title":"Fine-tuning is fine in federated learning","author":"Cheng","year":"2021","journal-title":"arXiv"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.00187","article-title":"Dispfl: towards communication-efficient personalized federated learning via decentralized sparse training","author":"Dai","year":"2022","journal-title":"arXiv"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09081","article-title":"Progressive skeletonization: trimming more fat from a network at initialization","author":"De Jorge","year":"2020","journal-title":"arXiv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1109\/JETCAS.2019.2910864","article-title":"Pre-defined sparse neural networks with hardware acceleration","volume":"9","author":"Dey","year":"2019","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.12395","article-title":"Data leakage in federated averaging","author":"Dimitrov","year":"2022","journal-title":"Trans. Mach. Learn. Res"},{"key":"B14","first-page":"14629","article-title":"\u201cFast sparse convnets,\u201d","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Elsen","year":"2020"},{"key":"B15","first-page":"2943","article-title":"\u201cRigging the lottery: making all tickets winners,\u201d","volume-title":"International Conference on Machine Learning","author":"Evci","year":"2020"},{"key":"B16","article-title":"\u201cThe lottery ticket hypothesis: finding sparse, trainable neural networks,\u201d","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Frankle","year":"2019"},{"key":"B17","article-title":"\u201cPruning neural networks at initialization: why are we missing the mark?\u201d","author":"Frankle","year":"2021","journal-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021"},{"key":"B18","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.dcn.2018.04.004","article-title":"Recruiting the abcd sample: design considerations and procedures","volume":"32","author":"Garavan","year":"2018","journal-title":"Dev. Cogn. Neurosci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"16937","DOI":"10.48550\/arXiv.2003.14053","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1510.00149","article-title":"Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.06335","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019","journal-title":"arXiv"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.01977","article-title":"Fedtiny: pruned federated learning towards specialized tiny models","author":"Huang","year":"2022","journal-title":"arXiv"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.11380","article-title":"Achieving personalized federated learning with sparse local models","author":"Huang","year":"2022","journal-title":"arXiv"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.15328","article-title":"Sparse random networks for communication-efficient federated learning","author":"Isik","year":"2022","journal-title":"arXiv"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101","article-title":"Model pruning enables efficient federated learning on edge devices","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B26","first-page":"1651","article-title":"\u201c$GAZELLE$: a low latency framework for secure neural network inferencem\u201d","volume-title":"27th USENIX security symposium (USENIX security 18)","author":"Juvekar","year":"2018"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.02527","article-title":"Federated optimization: distributed machine learning for on-device intelligence","author":"Kone\u010dn\u1ef3","year":"2016","journal-title":"arXiv"},{"key":"B28","article-title":"\u201cImagenet classification with deep convolutional neural networks,\u201d","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems, Volume 25"},{"key":"B29","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1109\/WorldS450073.2020.9210355","article-title":"\u201cSurvey of personalization techniques for federated learning,\u201d","volume-title":"2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4)","author":"Kulkarni","year":"2020"},{"key":"B30","doi-asserted-by":"publisher","first-page":"118579","DOI":"10.1016\/j.neuroimage.2021.118579","article-title":"Large, open datasets for human connectomics research: considerations for reproducible and responsible data use","volume":"244","author":"Laird","year":"2021","journal-title":"Neuroimage"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1016\/j.neuroimage.2015.05.049","article-title":"Coins data exchange: an open platform for compiling, curating, and disseminating neuroimaging data","volume":"124","author":"Landis","year":"2016","journal-title":"Neuroimage"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.02340","article-title":"Snip: single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.03371","article-title":"Lotteryfl: personalized and communication-efficient federated learning with lottery ticket hypothesis on non-iid datasets","author":"Li","year":"2020","journal-title":"arXiv"},{"key":"B34","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1145\/3485730.3485929","article-title":"\u201cFedmask: joint computation and communication-efficient personalized federated learning via heterogeneous masking,\u201d","volume-title":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","author":"Li","year":"2021"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3347","DOI":"10.1109\/TKDE.2021.3124599","article-title":"A survey on federated learning systems: vision, hype and reality for data privacy and protection","volume":"35","author":"Li","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B36","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/978-3-030-32692-0_16","article-title":"\u201cPrivacy-preserving federated brain tumour segmentation,\u201d","volume-title":"Machine Learning in Medical Imaging: 10th International Workshop, MLMI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 10","author":"Li","year":"2019"},{"key":"B37","doi-asserted-by":"publisher","first-page":"101765","DOI":"10.1016\/j.media.2020.101765","article-title":"Multi-site fmri analysis using privacy-preserving federated learning and domain adaptation: abide results","volume":"65","author":"Li","year":"2020","journal-title":"Med. Image Anal"},{"key":"B38","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.neunet.2019.08.015","article-title":"Transformed \u2113_1 regularization for learning sparse deep neural networks","volume":"119","author":"Ma","year":"2019","journal-title":"Neural Netw"},{"key":"B39","first-page":"1273","article-title":"\u201cCommunication-efficient learning of deep networks from decentralized data,\u201d","volume-title":"Artificial intelligence and statistics","author":"McMahan","year":"2017"},{"key":"B40","article-title":"\u201cCommunication-efficient learning of deep networks from decentralized data,\u201d","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"McMahan","year":"2016"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04976-1","article-title":"Assessment of the impact of shared brain imaging data on the scientific literature","author":"Milham","year":"2018","journal-title":"Nat. Commun"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1512","DOI":"10.12688\/f1000research.12353.1","article-title":"Coinstac: decentralizing the future of brain imaging analysis","volume":"6","author":"Ming","year":"2017","journal-title":"F1000Res"},{"key":"B43","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/SP.2017.12","article-title":"\u201cSecureml: a system for scalable privacy-preserving machine learning,\u201d","volume-title":"2017 IEEE symposium on security and privacy (SP)","author":"Mohassel","year":"2017"},{"key":"B44","article-title":"Skeletonization: a technique for trimming the fat from a network via relevance assessment","author":"Mozer","year":"1988","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.03896","article-title":"Explicit group sparse projection with applications to deep learning and NMF","author":"Ohib","year":"2022","journal-title":"Trans. Mach. Learn. Res"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.07488","article-title":"Salientgrads: sparse models for communication efficient and data aware distributed federated training","author":"Ohib","year":"2023","journal-title":"arXiv"},{"key":"B47","doi-asserted-by":"publisher","first-page":"22359","DOI":"10.1109\/ACCESS.2022.3151670","article-title":"Differential privacy for deep and federated learning: a survey","volume":"10","author":"Ouadrhiri","year":"2022","journal-title":"IEEE Access"},{"key":"B48","doi-asserted-by":"publisher","first-page":"204805","DOI":"10.3389\/fnins.2016.00365","article-title":"Coinstac: a privacy enabled model and prototype for leveraging and processing decentralized brain imaging data","volume":"10","author":"Plis","year":"2016","journal-title":"Front. Neurosci"},{"key":"B49","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3389\/fninf.2013.00012","article-title":"Toward open sharing of task-based fMRI data: the openfmri project","volume":"7","author":"Poldrack","year":"2013","journal-title":"Front. Neuroinform"},{"key":"B50","unstructured":"PoolJ.\n            SawarkarA.\n            RodgeJ.\n          Accelerating Inference with Sparsity Using the NVIDIA Ampere Architecture and NVIDIA TensorRT2021"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.02507","article-title":"Zerofl: efficient on-device training for federated learning with local sparsity","author":"Qiu","year":"2022","journal-title":"arXiv"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.00295","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020","journal-title":"arXiv"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.02389","article-title":"Comparing rewinding and fine-tuning in neural network pruning","author":"Renda","year":"2020","journal-title":"arXiv"},{"key":"B54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12021-021-09550-7","article-title":"Federated analysis of neuroimaging data: a review of the field","volume":"20","author":"Rootes-Murdy","year":"2022","journal-title":"Neuroinformatics"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.06731","article-title":"Braintorrent: a peer-to-peer environment for decentralized federated learning","author":"Roy","year":"2019","journal-title":"arXiv"},{"key":"B56","first-page":"92","article-title":"\u201cMulti-institutional deep learning modeling without sharing patient data: a feasibility study on brain tumor segmentation,\u201d","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part I 4","author":"Sheller","year":"2019"},{"key":"B57","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1109\/ISBI.2019.8759317","article-title":"\u201cFederated learning in distributed medical databases: meta-analysis of large-scale subcortical brain data,\u201d","volume-title":"2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019)","author":"Silva","year":"2019"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.04217","article-title":"Dynamic sparse training for deep reinforcement learning","author":"Sokar","year":"2021","journal-title":"arXiv"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.15789","article-title":"Ldp-fl: practical private aggregation in federated learning with local differential privacy","author":"Sun","year":"2020","journal-title":"arXiv"},{"key":"B60","article-title":"\u201cPruning neural networks without any data by iteratively conserving synaptic flow,\u201d","author":"Tanaka","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual"},{"key":"B61","doi-asserted-by":"publisher","first-page":"e21101","DOI":"10.1371\/journal.pone.0021101","article-title":"Data sharing by scientists: practices and perceptions","volume":"6","author":"Tenopir","year":"2011","journal-title":"PLoS ONE"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.00562","article-title":"Personalized federated learning by structured and unstructured pruning under data heterogeneity","author":"Vahidian","year":"2021","journal-title":"arXiv"},{"key":"B63","article-title":"\u201cPicking winning tickets before training by preserving gradient flow,\u201d","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Wang","year":"2020"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.09979","article-title":"Deephoyer: learning sparser neural network with differentiable scale-invariant sparsity measures","author":"Yang","year":"2019","journal-title":"arXiv"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.02903","article-title":"Applied federated learning: improving google keyboard query suggestions","author":"Yang","year":"2018","journal-title":"arXiv"},{"key":"B66","doi-asserted-by":"publisher","first-page":"103039","DOI":"10.1016\/j.cose.2022.103039","article-title":"Preserving data privacy in federated learning through large gradient pruning","volume":"125","author":"Zhang","year":"2023","journal-title":"Comput. Secur"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.00582","article-title":"Federated learning with non-iid data","author":"Zhao","year":"2018","journal-title":"arXiv"},{"key":"B68","article-title":"\u201cTo prune, or not to prune: exploring the efficacy of pruning for model compression,\u201d","author":"Zhu","year":"2018","journal-title":"6th International Conference on Learning Representations, ICLR 2018"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2024.1430987\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T00:44:06Z","timestamp":1725842646000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2024.1430987\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,9]]},"references-count":68,"alternative-id":["10.3389\/fninf.2024.1430987"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2024.1430987","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.05.14.594167","asserted-by":"object"}]},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,9]]},"article-number":"1430987"}}