{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:08:49Z","timestamp":1778692129999,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001774","name":"The University of Sydney","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001774","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Federated learning has gained significant attention for enabling effective model training on distributed data. However, in practice, most client data is unlabeled, and reliable communication with a central server is often infeasible at scale. To address this, we consider a more realistic setting where clients hold only unlabeled data and can communicate only with neighbors and propose DeNAV, a novel decentralized self-supervised learning framework for handling such scenarios. DeNAV simultaneously pre-trains multiple lightweight transformer models across clients. To improve training, we design a navigator algorithm to smartly plan the training route of each model and adopt staleness-aware model aggregation to handle the discrepancy of training status between models. DeNAV eliminates the need for server coordination, offering both convergence and consensus guarantees. Extensive experiments show that DeNAV is comparable to state-of-the-art federated self-supervised learning baselines and also surpasses previous decentralized methods with equal communication efficiency.<\/jats:p>","DOI":"10.1007\/s10994-025-06965-0","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:23:58Z","timestamp":1774970638000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeNAV: Decentralized Self-Supervised Learning with a Training Navigator"],"prefix":"10.1007","volume":"115","author":[{"given":"Xuanyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles Z.","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"6965_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., & He, K. (2021). Exploring simple Siamese representation learning. In Proceedings of CVPR (pp. 15750\u201315758).","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"6965_CR2","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of ICML (pp. 1597\u20131607)."},{"key":"6965_CR3","doi-asserted-by":"crossref","unstructured":"Chu, C. H., Lu, X., Awan, A. A., Subramoni, H., Hashmi, J., Elton, B., & Panda, D. K. (2017). Efficient and scalable multi-source streaming broadcast on GPU clusters for deep learning. In The Proceedings of the international conference on parallel processing (pp. 161\u2013170).","DOI":"10.1109\/ICPP.2017.25"},{"key":"6965_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of CVPR (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6965_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of ICLR."},{"key":"6965_CR6","doi-asserted-by":"publisher","first-page":"290","DOI":"10.5486\/PMD.1959.6.3-4.12","volume":"6","author":"P Erdos","year":"1959","unstructured":"ERDdS, P. (1959). On random graphs I. Publicationes Mathematicae, 6, 290\u2013297.","journal-title":"Publicationes Mathematicae Debrecen"},{"key":"6965_CR7","unstructured":"Even, M. (2023). Stochastic gradient descent under Markovian sampling schemes. In International conference on machine learning (pp. 9412\u20139439)."},{"key":"6965_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of CVPR (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"6965_CR9","doi-asserted-by":"crossref","unstructured":"Heged\u0171s, I., Danner, G., & Jelasity, M. (2019). Gossip learning as a decentralized alternative to federated learning. In Distributed applications and interoperable systems (pp. 74\u201390).","DOI":"10.1007\/978-3-030-22496-7_5"},{"key":"6965_CR10","unstructured":"Hsu, T.-M.H., Qi, H., & Brown, M. (2019). Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint. Retrieved from arXiv:1909.06335."},{"key":"6965_CR11","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images (Technical Report No. TR-2009). University of Toronto."},{"key":"6965_CR12","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019). ALBERT: A lite BERT for self-supervised learning of language representations. In ICLR Proceedings."},{"key":"6965_CR13","unstructured":"Lian, X., Zhang, C., Zhang, H., Hsieh, C. J., Zhang, W., & Liu, J. (2017). Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent. (Vol.\u00a030, pp. 5331\u20135341)."},{"key":"6965_CR14","doi-asserted-by":"crossref","unstructured":"Liao, X., Liu, W., Chen, C., Zhou, P., Yu, F., Zhu, H., Yao, B., Wang, T., Zheng, X., & Tan, Y. (2024). Rethinking the representation in federated unsupervised learning with non-IID data. In Proceedings of CVPR (pp. 22841\u201322850).","DOI":"10.1109\/CVPR52733.2024.02155"},{"key":"6965_CR15","doi-asserted-by":"crossref","unstructured":"Liu, L., Zhang, J., Song, S., & Letaief, K.B. (2020). Client-edge-cloud hierarchical federated learning. In Proceedings of ICC (pp. 1\u20136).","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"6965_CR16","unstructured":"Lubana, E. S., Tang, C. I., Kawsar, F., Dick, R. P., & Mathur, A. (2022). Orchestra: Unsupervised federated learning via globally consistent clustering. In Proceedings of ICML (pp. 14461\u201314484)."},{"key":"6965_CR17","first-page":"2229","volume":"32","author":"X Ma","year":"2019","unstructured":"Ma, X., Zhang, P., Zhang, S., Duan, N., Hou, Y., Zhou, M., & Song, D. (2019). A tensorized transformer for language modeling. NeurIPS Proceedings,32, 2229\u20132239.","journal-title":"NeurIPS Proceedings"},{"key":"6965_CR18","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of AISTATS (pp. 1273\u20131282)."},{"key":"6965_CR19","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M. L. (2014). Markov decision processes: Discrete stochastic dynamic programming. Wiley."},{"key":"6965_CR20","doi-asserted-by":"crossref","unstructured":"Rehman, Y. A. U., Gao, Y., De\u00a0Gusm\u00e3o, P. P. B., Alibeigi, M., Shen, J., & Lane, N. D. (2023). L-dawa: Layer-wise divergence aware weight aggregation in federated self-supervised visual representation learning. In Proceedings of IEEE international conference on computer vision (pp. 16464\u201316473).","DOI":"10.1109\/ICCV51070.2023.01509"},{"issue":"1","key":"6965_CR21","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/TCNS.2022.3203361","volume":"10","author":"R Singh","year":"2023","unstructured":"Singh, R., Gupta, A., & Shroff, N. B. (2023). Learning in constrained Markov decision processes. IEEE Transactions on Control of Network Systems,10(1), 441\u2013453.","journal-title":"IEEE Transactions on Control of Network Systems"},{"key":"6965_CR22","unstructured":"Sun, T., Li, D., & Wang, B. (2022). Adaptive random walk gradient descent for decentralized optimization. In Proceedings of ICML (pp. 20790\u201320809)."},{"key":"6965_CR23","unstructured":"Tang, Z., Shi, S., Wang, W., Li, B., & Chu, X. (2020). Communication-efficient distributed deep learning: A comprehensive survey. arXiv preprint. Retrieved from arXiv:2003.06307."},{"issue":"3","key":"6965_CR24","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/TPDS.2022.3230938","volume":"34","author":"Z Tang","year":"2022","unstructured":"Tang, Z., Shi, S., Li, B., & Chu, X. (2022). GossipFL: A decentralized federated learning framework with sparsified and adaptive communication. IEEE Transactions on Parallel and Distributed Systems,34(3), 909\u2013922.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"6965_CR26","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141, & Polosukhin, I. (2017). Attention is all you need. NeurIPS Proceedings,30, 5998\u20136008.","journal-title":"NeurIPS Proceedings"},{"key":"6965_CR27","first-page":"3630","volume":"29","author":"O Vinyals","year":"2016","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching networks for one shot learning. NeurIPS Proceedings, 29, 3630\u20133638.","journal-title":"NeurIPS Proceedings"},{"key":"6965_CR25","unstructured":"Visipedia, & iNaturalist. (2021). Mini inaturalist 2021 dataset. https:\/\/github.com\/visipedia\/inat_comp"},{"key":"6965_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, H., Liu, J., & Zhang, Y. (2021). Resource-efficient federated learning with hierarchical aggregation in edge computing. In Proceedings of the IEEE international conference on computer communications (pp. 1\u201310).","DOI":"10.1109\/INFOCOM42981.2021.9488756"},{"key":"6965_CR29","unstructured":"Wang, L., Zhang, K., Li, Y., Tian, Y., & Tedrake, R. (2022). Does learning from decentralized non-IID unlabeled data benefit from self supervision? In ICLR Proceedings"},{"key":"6965_CR30","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","volume":"15","author":"K Wei","year":"2020","unstructured":"Wei, K., Li, J., Ding, M., & Ma, C. (2020). Federated learning with differential privacy: Algorithms and performance analysis. IEEE Transactions on Information Forensics and Security,15, 3454\u20133469.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"6965_CR31","unstructured":"Yang, N., Chen, X., Liu, C.Z., Yuan, D., Bao, W., & Cui, L. (2023). Fedmae: Federated self-supervised learning with one-block masked auto-encoder. Retrieved from arXiv:2303.11339."},{"key":"6965_CR32","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","volume":"94","author":"D Yarotsky","year":"2017","unstructured":"Yarotsky, D. (2017). Error bounds for approximations with deep ReLU networks. Neural Networks,94, 103\u2013114.","journal-title":"Neural Networks"},{"key":"6965_CR33","first-page":"27127","volume":"35","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., Wang, Y., & Wang, Y. (2022). How mask matters: Towards theoretical understandings of masked autoencoders. NeurIPS Proceedings, 35, 27127\u201327139.","journal-title":"NeurIPS Proceedings"},{"key":"6965_CR34","doi-asserted-by":"crossref","unstructured":"Zhuang, W., Gan, X., Wen, Y., Zhang, S., & Yi, S. (2021). Collaborative unsupervised visual representation learning from decentralized data. In Proceedings of IEEE international conference on computer vision (pp. 4912\u20134921).","DOI":"10.1109\/ICCV48922.2021.00487"},{"key":"6965_CR35","unstructured":"Zhuang, W., Wen, Y., & Zhang, S. (2021). Divergence-aware federated self-supervised learning. In Proceedings of international conference on learning representations"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06965-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06965-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06965-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T16:08:07Z","timestamp":1778688487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06965-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["6965"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06965-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"2 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"82"}}