{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T23:01:28Z","timestamp":1782514888793,"version":"3.54.5"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T00:00:00Z","timestamp":1736035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T00:00:00Z","timestamp":1736035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Hong Kong Research Grants Council (RGC) General Research Fund","award":["Grant 14220622"],"award-info":[{"award-number":["Grant 14220622"]}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission - Hong Kong","doi-asserted-by":"publisher","award":["ITS\/229\/22"],"award-info":[{"award-number":["ITS\/229\/22"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Federated semi-supervised learning (FSSL) target to address the increasing privacy concerns for the practical scenarios, where data holders are limited in labeling capability. Latest FSSL approaches leverage the prediction consistency between the local model and global model to exploit knowledge from partially labeled or completely unlabeled clients. However, they merely utilize data-level augmentation for prediction consistency and simply aggregate model parameters through the weighted average at the server, which leads to biased classifiers and suffers from skewed unlabeled clients. To remedy these issues, we present a novel FSSL framework, Relation-guided Versatile Regularization (FedRVR), consisting of versatile regularization at clients and relation-guided directional aggregation strategy at the server. In versatile regularization, we propose the model-guided regularization together with the data-guided one, and encourage the prediction of the local model invariant to two extreme global models with different abilities, which provides richer consistency supervision for local training. Moreover, we devise a relation-guided directional aggregation at the server, in which a parametric relation predictor is introduced to yield pairwise model relation and obtain a model ranking. In this manner, the server can provide a superior global model by aggregating relative dependable client models, and further produce an inferior global model via reverse aggregation to promote the versatile regularization at clients. Extensive experiments on three FSSL benchmarks verify the superiority of FedRVR over state-of-the-art counterparts across various federated learning settings.<\/jats:p>","DOI":"10.1007\/s11263-024-02330-1","type":"journal-article","created":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T04:38:13Z","timestamp":1736051893000},"page":"3312-3326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Relation-Guided Versatile Regularization for Federated Semi-Supervised Learning"],"prefix":"10.1007","volume":"133","author":[{"given":"Qiushi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0853-6948","authenticated-orcid":false,"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,5]]},"reference":[{"key":"2330_CR1","unstructured":"Berthelot, D., Carlini, N., Cubuk, E.D., Kurakin, A., Sohn, K., Zhang, H., Raffel, C. (2019). Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. Proc. ICLR Vol. abs\/1911.09785."},{"key":"2330_CR2","first-page":"5050","volume":"32","author":"D Berthelot","year":"2019","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., & Raffel, C. A. (2019). Mixmatch: A holistic approach to semi-supervised learning. Proceeding NeurIPS, 32, 5050\u20135060.","journal-title":"Proceeding NeurIPS"},{"key":"2330_CR3","first-page":"6912","volume":"35","author":"P Cascante-Bonilla","year":"2020","unstructured":"Cascante-Bonilla, P., Tan, F., Qi, Y., & Ordonez, V. (2020). Curriculum labeling: Revisiting pseudo-labeling for semi-supervised learning. Proceeding AAAI, 35, 6912\u20136920.","journal-title":"Proceeding AAAI"},{"key":"2330_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Guo, Y., Chen, Q., Li, M., Zeng, W., Wang, Y., & Tan, M. (2021). Contrastive neural architecture search with neural architecture comparators. - Proc. CVPR pp. 9502\u20139511.","DOI":"10.1109\/CVPR46437.2021.00938"},{"key":"2330_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, W., Xing, X., & Yuan, Y. (2023). Medical federated learning with joint graph purification for noisy label learning. Med image anal Vol.\u00a090, pp. 102976\u2013102988. Elsevier.","DOI":"10.1016\/j.media.2023.102976"},{"key":"2330_CR6","doi-asserted-by":"publisher","first-page":"3663","DOI":"10.1109\/TMI.2022.3192483","volume":"41","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Yang, C., Zhu, M., Peng, Z., & Yuan, Y. (2022). Personalized retrogress-resilient federated learning towards imbalanced medical data. IEEE Transactions on Medical Imaging, 41, 3663\u20133674.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2330_CR7","first-page":"347","volume":"24","author":"Z Chen","year":"2021","unstructured":"Chen, Z., Zhu, M., Yang, C., & Yuan, Y. (2021). Personalized retrogress-resilient framework for real-world medical federated learning. Proceeding MICCAI, 24, 347\u2013356.","journal-title":"Proceeding MICCAI"},{"key":"2330_CR8","doi-asserted-by":"crossref","unstructured":"Cho, Y.J., Joshi, G., &Dimitriadis, D. (2023). Local or global: Selective knowledge assimilation for federated learning with limited labels. Proc. ICCV pp. 17087\u201317096.","DOI":"10.1109\/ICCV51070.2023.01567"},{"key":"2330_CR9","unstructured":"Codella, N., Rotemberg, V., Tschandl, P., Celebi, M.E., Dusza, S., & Gutman, D. others (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368."},{"key":"2330_CR10","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., & Le, Q.V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. CVPR Workshops pp. 702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2330_CR11","unstructured":"Diao, E., Ding, J., & Tarokh, V. (2021). - Semifl: Communication efficient semi-supervised federated learning with unlabeled clients. Proc. NeurIPS pp. 17871\u201317884."},{"key":"2330_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-021-00431-6","volume":"4","author":"Q Dou","year":"2021","unstructured":"Dou, Q., So, T. Y., Jiang, M., Liu, Q., Vardhanabhuti, V., Kaissis, G., et al. (2021). Federated deep learning for detecting covid-19 lung abnormalities in ct: a privacy-preserving multinational validation study. NPJ Digital Medicine, 4, 1\u201311.","journal-title":"NPJ Digital Medicine"},{"key":"2330_CR13","doi-asserted-by":"crossref","unstructured":"Fan, C., Hu, J., & Huang, J. (2022). - Private semi-supervised federated learning. Proc. IJCAI pp. 2009\u20132015.","DOI":"10.24963\/ijcai.2022\/279"},{"key":"2330_CR14","doi-asserted-by":"crossref","unstructured":"Gao, L., Fu, H., Li, L., Chen, Y., Xu, M., & Xu, C- Z. (2022). Feddc: Federated learning with non-iid data via local drift decoupling and correction. Proc. CVPR pp. 10112\u201310121.","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"2330_CR15","doi-asserted-by":"crossref","unstructured":"Gong, C., Wang, D., & Liu, Q. (2021). - Alphamatch: Improving consistency for semi-supervised learning with alpha-divergence. Proc. CVPR pp. 13683\u201313692.","DOI":"10.1109\/CVPR46437.2021.01347"},{"key":"2330_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. - Proc. CVPR pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2330_CR17","doi-asserted-by":"crossref","unstructured":"Hu, Z., Yang, Z., Hu, X., & Nevatia, R. (2021). Simple: Similar pseudo label exploitation for semi-supervised classification. Proc. CVPR pp. 15099\u201315108.","DOI":"10.1109\/CVPR46437.2021.01485"},{"key":"2330_CR18","doi-asserted-by":"crossref","unstructured":"Huang, M., Huang, Z., Li, C., Chen, X., Xu, H., Li, Z., & Liang, X. (2022). Arch-graph: Acyclic architecture relation predictor for task-transferable neural architecture search. Proc. CVPR pp. 11881\u201311891.","DOI":"10.1109\/CVPR52688.2022.01158"},{"key":"2330_CR19","unstructured":"Huang, T., Sun, Y., Wang, X., Yao, H., & Zhang, C. (2021). Spatial ensemble: a novel model smoothing mechanism for student-teacher framework. Proceeding NeurIPS pp. 15957\u201315968."},{"key":"2330_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chu, L., Zhou, Z., Wang, L., Liu, J., Pei, J., & Zhang, Y. (2021). Personalized cross-silo federated learning on non-iid data. Proceeding AAAI pp. 7865\u20137873.","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"2330_CR21","unstructured":"Jeong, W., Yoon, J., Yang, E., Hwang, S.J. (2020). Federated semi-supervised learning with inter-client consistency & disjoint learning. arxiv preprint arxiv:2006.12097."},{"key":"2330_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, M., Yang, H., Li, X., Liu, Q., Heng, P- A., & Dou, Q. (2022). Dynamic bank learning for semi-supervised federated image diagnosis with class imbalance. - Proceeding MICCAI Vol. 13433, pp. 196\u2013206.","DOI":"10.1007\/978-3-031-16437-8_19"},{"key":"2330_CR23","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al. (2009). Learning multiple layers of features from tiny images. - Technical Report."},{"key":"2330_CR24","doi-asserted-by":"crossref","unstructured":"Kuo, C- W., Ma, C- Y., Huang, J- B., & Kira, Z. (2020). Featmatch: Feature-based augmentation for semi-supervised learning. ECCV, 12363, 479\u2013495.","DOI":"10.1007\/978-3-030-58523-5_28"},{"key":"2330_CR25","unstructured":"Laine, S., & Aila, T. (2016). Temporal ensembling for semi-supervised learning. - arxiv preprint arxiv:1610.02242."},{"key":"2330_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Xiong, C., & Hoi, S.C. (2021). - Comatch: Semi-supervised learning with contrastive graph regularization. ICCV pp. 9475\u20139484.","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"2330_CR27","doi-asserted-by":"crossref","unstructured":"Li, M., Li, Q., & Wang, Y. (2023). Class balanced adaptive pseudo labeling for federated semi-supervised learning. Proceeding CVPR pp. 16292\u201316301.","DOI":"10.1109\/CVPR52729.2023.01563"},{"key":"2330_CR28","first-page":"429","volume":"2","author":"T Li","year":"2020","unstructured":"Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated optimization in heterogeneous networks. Proc. MLSys, 2, 429\u2013450.","journal-title":"Proc. MLSys"},{"key":"2330_CR29","unstructured":"Li, X., Jiang, M., Zhang, X., Kamp, M., & Dou, Q. (2021). Fedbn: Federated learning on non-iid features via local batch normalization. arxiv preprint arxiv:2102.07623."},{"key":"2330_CR30","doi-asserted-by":"crossref","unstructured":"Li, X- C., Xu, Y- C., Song, S., Li, B., Li, Y., Shao, Y., & Zhan, D- C. (2022). Federated learning with position-aware neurons. Proceeding CVPR pp. 10082\u201310091.","DOI":"10.1109\/CVPR52688.2022.00984"},{"key":"2330_CR31","doi-asserted-by":"crossref","unstructured":"Liang, X., Lin, Y., Fu, H., Zhu, L., Li, X. (2022). Rscfed: Random sampling consensus federated semi-supervised learning. Proceeding CVPR pp. 10154\u201310163.","DOI":"10.1109\/CVPR52688.2022.00991"},{"key":"2330_CR32","first-page":"325","volume":"64","author":"Q Liu","year":"2021","unstructured":"Liu, Q., Yang, H., Dou, Q., & Heng, P.-A. (2021). Federated semi-supervised medical image classification via inter-client relation matching. Proceeding MICCAI, 64, 325\u2013335.","journal-title":"Proceeding MICCAI"},{"key":"2330_CR33","doi-asserted-by":"publisher","first-page":"3837","DOI":"10.1609\/aaai.v38i4.28175","volume":"38","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Wu, H., & Qin, J. (2024). Fedcd: Federated semi-supervised learning with class awareness balance via dual teachers. Proceedings AAAI, 38, 3837\u20133845.","journal-title":"Proceedings AAAI"},{"key":"2330_CR34","unstructured":"Long, Z., Che, L., Wang, Y., Ye, M., Luo, W.J.X.H., & Junyu, Ma, F. (2020). Fedsemi: An adaptive federated semi-supervised learning framework. arXiv preprint arXiv:2012.03292."},{"key":"2330_CR35","unstructured":"Loshchilov, I., & Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. - arxiv preprint arxiv:1608.03983."},{"key":"2330_CR36","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B.A. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings AISTATS pp. 1273\u20131282."},{"key":"2330_CR37","doi-asserted-by":"crossref","unstructured":"Mendieta, M., Yang, T., Wang, P., Lee, M., Ding, Z., & Chen, C. (2022). Local learning matters: Rethinking data heterogeneity in federated learning. Proc. CVPR pp. 8397\u20138406.","DOI":"10.1109\/CVPR52688.2022.00821"},{"key":"2330_CR38","doi-asserted-by":"crossref","unstructured":"Miyato, T., Maeda, S- I., Koyama, M., Ishii, S. (2018). Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE TPAMI,41, 1979\u20131993.","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"2330_CR39","first-page":"8024","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., et al. (2019). Pytorch: An imperative style, high-performance deep learning library. Proceedings NeurIPS, 32, 8024\u20138035.","journal-title":"Proceedings NeurIPS"},{"key":"2330_CR40","unstructured":"Sohn, K., Berthelot, D., Li, C-L., Zhang, Z., Carlini, N., Cubuk, E.D., Raffel, C. (2020). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Proc. NeurIPS,33, 596\u2013608."},{"key":"2330_CR41","first-page":"1139","volume":"28","author":"I Sutskever","year":"2013","unstructured":"Sutskever, I., Martens, J., Dahl, G., & Hinton, G. (2013). On the importance of initialization and momentum in deep learning. Proceedings ICML, 28, 1139-1147.","journal-title":"Proceedings ICML"},{"key":"2330_CR42","first-page":"1195","volume":"30","author":"A Tarvainen","year":"2017","unstructured":"Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. - Proc. NeurIPS, 30, 1195\u20131204.","journal-title":"NeurIPS"},{"key":"2330_CR43","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-sne. JMLR, 9, 2579\u20132605.","journal-title":"JMLR"},{"key":"2330_CR44","unstructured":"Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., & Khazaeni, Y. (2020). Federated learning with matched averaging. arxiv preprint arxiv:2002.06440."},{"key":"2330_CR45","doi-asserted-by":"crossref","unstructured":"Wen, W., Liu, H., Chen, Y., Li, H., Bender, G., & Kindermans, P- J. (2020). Neural predictor for neural architecture search. Proc. ECCV,12374, 660\u2013676.","DOI":"10.1007\/978-3-030-58526-6_39"},{"key":"2330_CR46","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M- T., & Le, Q.V. (2020). Unsupervised data augmentation for consistency training. Proc. NeurIPS,33, 6256\u20136268."},{"key":"2330_CR47","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M- T., Hovy, E., & Le, Q.V. (2020). Self-training with noisy student improves imagenet classification. Proc. CVPR pp. 10687\u201310698.","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"2330_CR48","unstructured":"Xu, Y., Shang, L., Ye, J., Qian, Q., Li, Y- F., Sun, B., & Jin, R. (2021). Dash: Semi-supervised learning with dynamic thresholding. Proceedings ICML,139, 11525\u201311536."},{"key":"2330_CR49","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, Y., Han, K., Tang, Y., Jui, S., Xu, C., & Xu, C. (2021). Renas: Relativistic evaluation of neural architecture search. Proc. CVPR pp. 4411\u20134420.","DOI":"10.1109\/CVPR46437.2021.00439"},{"key":"2330_CR50","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1109\/TMI.2023.3247440","volume":"42","author":"Q Yang","year":"2023","unstructured":"Yang, Q., Chen, Z., & Yuan, Y. (2023). Hierarchical bias mitigation for semi-supervised medical image classification. IEEE Trans Med Imag, 42, 2200\u20132210.","journal-title":"IEEE Trans Med Imag"},{"key":"2330_CR51","first-page":"119","volume":"13438","author":"Q Yang","year":"2022","unstructured":"Yang, Q., Liu, X., Chen, Z., Ibragimov, B., & Yuan, Y. (2022). Semi-supervised medical image classification with temporal knowledge-aware regularization. Proc. MICCAI, 13438, 119\u2013129.","journal-title":"Proc. MICCAI"},{"key":"2330_CR52","unstructured":"Zagoruyko, S. (2016). Wide residual networks. arxiv preprint arxiv:1605.07146."},{"key":"2330_CR53","first-page":"18408","volume":"34","author":"B Zhang","year":"2021","unstructured":"Zhang, B., Wang, Y., Hou, W., Wu, H., Wang, J., Okumura, M., & Shinozaki, T. (2021). Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. - Proc. NeurIPS, 34, 18408\u201318419.","journal-title":"NeurIPS"},{"key":"2330_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, L., Luo, Y., Bai, Y., Du, B., & Duan, L- Y. (2021). Federated learning for non-iid data via unified feature learning and optimization objective alignment. - Proc. ICCV pp. 4420\u20134428.","DOI":"10.1109\/ICCV48922.2021.00438"},{"key":"2330_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, L., Shen, L., Ding, L., Tao, D., & Duan, L-Y. (2022). Fine-tuning global model via data-free knowledge distillation for non-iid federated learning. Proc. CVPR pp. 10174\u201310183.","DOI":"10.1109\/CVPR52688.2022.00993"},{"key":"2330_CR56","unstructured":"Zhang, Z., Yao, Z., Yang, Y., Yan, Y., Gonzalez, J.E., & Mahoney, M.W. (2020). Benchmarking semi-supervised federated learning. arXiv preprint arXiv:2008.11364."},{"key":"2330_CR57","first-page":"11523","volume":"119","author":"T Zhou","year":"2020","unstructured":"Zhou, T., Wang, S., & Bilmes, J. (2020). Time-consistent self-supervision for semi-supervised learning. Proc. ICML, 119, 11523\u201311533.","journal-title":"Proc. ICML"},{"key":"2330_CR58","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TMI.2023.3294014","volume":"43","author":"M Zhu","year":"2023","unstructured":"Zhu, M., Liao, J., Liu, J., & Yuan, Y. (2023). Fedoss: Federated open set recognition via inter-client discrepancy and collaboration. IEEE Trans Med Imag, 43, 190\u2013202.","journal-title":"IEEE Trans Med Imag"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02330-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02330-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02330-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:52:57Z","timestamp":1746859977000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02330-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,5]]},"references-count":58,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2330"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02330-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,5]]},"assertion":[{"value":"30 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}