{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T18:53:04Z","timestamp":1751395984953,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434143"},{"type":"electronic","value":"9783031434150"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43415-0_10","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:01:51Z","timestamp":1694851311000},"page":"156-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["R\u00e9nyi Divergence Deep Mutual Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4620-6912","authenticated-orcid":false,"given":"Weipeng Fuzzy","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changbo","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqiang","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyuan","family":"Piao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"key":"10_CR1","unstructured":"Ajalloeian, A., Stich, S.U.: Analysis of SGD with biased gradient estimators. In: Workshop on \u201cBeyond First Order Methods in ML System\u201d (2020)"},{"issue":"2","key":"10_CR2","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1007\/s00145-017-9265-9","volume":"31","author":"S Bai","year":"2018","unstructured":"Bai, S., Lepoint, T., Roux-Langlois, A., Sakzad, A., Stehl\u00e9, D., Steinfeld, R.: Improved security proofs in lattice-based cryptography: using the r\u00e9nyi divergence rather than the statistical distance. J. Cryptol. 31(2), 610\u2013640 (2018)","journal-title":"J. Cryptol."},{"key":"10_CR3","unstructured":"Cheng, X., Bartlett, P.: Convergence of Langevin MCMC in KL-divergence. In: Algorithmic Learning Theory, pp. 186\u2013211. PMLR (2018)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"10_CR5","unstructured":"Erhan, D., Courville, A., Bengio, Y., Vincent, P.: Why does unsupervised pre-training help deep learning? In: JMLR, pp. 201\u2013208 (2010)"},{"key":"10_CR6","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","volume":"60","author":"TV Erven","year":"2014","unstructured":"Erven, T.V., Harr\u00ebmos, P.: R\u00e9nyi divergence and Kullback-Leibler divergence. IEEE Trans. Inf. Theory 60, 3797\u20133820 (2014). https:\/\/doi.org\/10.1109\/TIT.2014.2320500","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"6","key":"10_CR7","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129(6), 1789\u20131819 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR9","unstructured":"Honorio, J.: Lipschitz parametrization of probabilistic graphical models. In: Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2011, pp. 347\u2013354. AUAI Press, Arlington (2011)"},{"key":"10_CR10","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s10107-020-01486-1","volume":"187","author":"B Hu","year":"2021","unstructured":"Hu, B., Seiler, P., Lessard, L.: Analysis of biased stochastic gradient descent using sequential semidefinite programs. Math. Program. 187, 383\u2013408 (2021)","journal-title":"Math. Program."},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)","DOI":"10.18653\/v1\/E17-2068"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Kingma, D.P., Welling, M.: An introduction to variational autoencoders. Found. Trends\u00ae Mach. Learn. 12(4), 307\u2013392 (2019)","DOI":"10.1561\/2200000056"},{"key":"10_CR13","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"10_CR14","unstructured":"Li, Y., Turner, R.E.: R\u00e9nyi divergence variational inference. In: NeurIPS, vol. 29 (2016)"},{"key":"10_CR15","unstructured":"Masumura, R., Ihori, M., Takashima, A., Tanaka, T., Ashihara, T.: End-to-end automatic speech recognition with deep mutual learning. In: APSIPA ASC, pp. 632\u2013637. IEEE (2020)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Mironov, I.: R\u00e9nyi differential privacy. In: 2017 IEEE 30th Computer Security Foundations Symposium (CSF), pp. 263\u2013275. IEEE (2017)","DOI":"10.1109\/CSF.2017.11"},{"key":"10_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","author":"Y Nesterov","year":"2003","unstructured":"Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-1-4419-8853-9"},{"key":"10_CR18","unstructured":"Nguyen, L., Nguyen, P.H., Dijk, M., Richt\u00e1rik, P., Scheinberg, K., Tak\u00e1c, M.: Sgd and hogwild! convergence without the bounded gradients assumption. In: International Conference on Machine Learning, pp. 3750\u20133758. PMLR (2018)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"10_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-030-66415-2_49","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"W Park","year":"2020","unstructured":"Park, W., Kim, W., You, K., Cho, M.: Diversified mutual learning for deep metric learning. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12535, pp. 709\u2013725. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66415-2_49"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Prest, T.: Sharper bounds in lattice-based cryptography using the R\u00e9nyi divergence. In: International Conference on the Theory and Application of Cryptology and Information Security, pp. 347\u2013374 (2017)","DOI":"10.1007\/978-3-319-70694-8_13"},{"key":"10_CR23","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"issue":"4","key":"10_CR24","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1162\/neco_01484","volume":"34","author":"N Sajid","year":"2022","unstructured":"Sajid, N., Faccio, F., Da Costa, L., Parr, T., Schmidhuber, J., Friston, K.: Bayesian brains and the R\u00e9nyi divergence. Neural Comput. 34(4), 829\u2013855 (2022). https:\/\/doi.org\/10.1162\/neco_01484","journal-title":"Neural Comput."},{"key":"10_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"issue":"56","key":"10_CR26","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(56), 1929\u20131958 (2014)","journal-title":"JMLR"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going Deeper with Convolutions, 10. arXiv preprint arXiv:1409.4842 (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10_CR29","unstructured":"Wang, Y.X., Balle, B., Kasiviswanathan, S.P.: Subsampled R\u00e9nyi differential privacy and analytical moments accountant. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 1226\u20131235. PMLR (2019)"},{"key":"10_CR30","unstructured":"Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)"},{"key":"10_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-58452-8_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Yang","year":"2020","unstructured":"Yang, T., Zhu, S., Chen, C., Yan, S., Zhang, M., Willis, A.: MutualNet: adaptive ConvNet via mutual learning from network width and resolution. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 299\u2013315. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_18"},{"key":"10_CR32","doi-asserted-by":"publisher","first-page":"103770","DOI":"10.1016\/j.bspc.2022.103770","volume":"77","author":"H Zhang","year":"2022","unstructured":"Zhang, H., et al.: DCML: deep contrastive mutual learning for COVID-19 recognition. Biomed. Signal Process. Control 77, 103770 (2022)","journal-title":"Biomed. Signal Process. Control"},{"key":"10_CR33","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: NeurIPS, vol. 28 (2015)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: CVPR, pp. 4320\u20134328 (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"10_CR35","doi-asserted-by":"publisher","first-page":"107796","DOI":"10.1016\/j.patcog.2020.107796","volume":"112","author":"H Zhao","year":"2021","unstructured":"Zhao, H., Yang, G., Wang, D., Lu, H.: Deep mutual learning for visual object tracking. Pattern Recogn. 112, 107796 (2021)","journal-title":"Pattern Recogn."},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, J., Luo, W., Chen, B., Gilman, A.: Mutual-learning improves end-to-end speech translation. In: EMNLP, pp. 3989\u20133994 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.325"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43415-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:04:14Z","timestamp":1694851454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43415-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434143","9783031434150"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43415-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}