{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:47:38Z","timestamp":1782312458334,"version":"3.54.5"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061058","type":"print"},{"value":"9783032061065","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06106-5_14","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:08:26Z","timestamp":1759399706000},"page":"235-253","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning from\u00a0Stochastic Teacher Representations Using Student-Guided Knowledge Distillation"],"prefix":"10.1007","author":[{"given":"Muhammad Haseeb","family":"Aslam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clara","family":"Martinez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Pedersoli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro Lameiras","family":"Koerich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Granger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"14_CR1","unstructured":"Allen-Zhu, Z., Li, Y.: Towards understanding ensemble, knowledge distillation and self-distillation in deep learning. ICLR (2020)"},{"key":"14_CR2","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: ESANN (2013)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Aslam, M.H., Osama\u00a0Zeeshan, M., Pedersoli, M., Koerich, A.L., Bacon, S., Granger, E.: Privileged knowledge distillation for dimensional emotion recognition in the wild. In: IEEE\/CVF CVPRw (2023)","DOI":"10.1109\/CVPRW59228.2023.00336"},{"key":"14_CR4","unstructured":"Borup, K., Andersen, L.N.: Even your teacher needs guidance: ground-truth targets dampen regularization imposed by self-distillation. arXiv 2102.13088 (2021)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Bucilua, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD. Association for Computing Machinery (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chaptoukaev, H., Strizhkova, V., et\u00a0al., M.P.: StressID: a multimodal dataset for stress identification. In: Neural IPS Datasets and Benchmarks Track (2023)","DOI":"10.52202\/075280-1297"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, N., Zhang, Z.: DarkRank: accelerating deep metric learning via cross sample similarities transfer (2017)","DOI":"10.1609\/aaai.v32i1.11783"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Dau, H.A., et\u00a0al.: The UCR time series archive. IEEE\/CAA J. Autom. Sinica 6(6), 1293\u20131305 (2019)","DOI":"10.1109\/JAS.2019.1911747"},{"key":"14_CR9","unstructured":"Fort, S., Hu, H., Lakshminarayanan, B.: Deep ensembles: a loss landscape perspective. arXiv 1912.02757 (2020)"},{"key":"14_CR10","unstructured":"Furlanello, T., Lipton, Z.C., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks. In: ICML (2018)"},{"key":"14_CR11","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. ICML 48 (2016)"},{"key":"14_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv 1503.02531 (2015)"},{"key":"14_CR13","unstructured":"Hu, E.J., et al.: LORA: low-rank adaptation of large language models (2021)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Ji, X., Zhao, T., Li, W., Zomaya, A.: Automatic pain assessment with ultra-short electrodermal activity signal. SAC \u201923. In: ACM (2023)","DOI":"10.1145\/3555776.3577721"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, M., Rosio, R., et\u00a0al., S.S.: Personalized and adaptive neural networks for pain detection from multi-modal physiological features. ESWA 235 (2024)","DOI":"10.1016\/j.eswa.2023.121082"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"K\u00e4chele, M., Thiam, P., Amirian, M.E.A.: Methods for person-centered continuous pain intensity assessment from bio-physiological channels. IEEE JSTSP 10(5), 854\u2013864 (2016)","DOI":"10.1109\/JSTSP.2016.2535962"},{"key":"14_CR17","unstructured":"Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: NeurIPS (2017)"},{"key":"14_CR18","unstructured":"Lee, S., Park, T., Lee, K.: Soft contrastive learning for time series. In: ICLR (2024)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Lin, M., Wang, Y., Wu, Y., Tian, Y., Shao, L., Ji, R.: Distilling a powerful student model via online knowledge distillation. IEEE TNNLS 34(11), 8743\u20138752 (2023)","DOI":"10.1109\/TNNLS.2022.3152732"},{"key":"14_CR20","unstructured":"Li, Y. et al.: Ensembles of low-rank expert adapters (2025)"},{"key":"14_CR21","unstructured":"Lin, T., et al: Ensemble distillation for robust model fusion in fed. learning (2021)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Lopez-Martinez, D., Picard, R.: Continuous pain intensity estimation from autonomic signals with recurrent neural networks. In: IEEE EMBC 2018","DOI":"10.1109\/EMBC.2018.8513575"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Lopez-Martinez, D., Picard, R.: Multi-task neural networks for personalized pain recognition from physiological signals. In: IEEE ACIIw (2017)","DOI":"10.1109\/ACIIW.2017.8272611"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Lu, Z., Ozek, B., Kamarthi, S.: Transformer encoder with multiscale deep learning for pain classification using physiological signals. Front. Phys. 14 (2023)","DOI":"10.3389\/fphys.2023.1294577"},{"key":"14_CR25","unstructured":"Mobahi, H., Farajtabar, M., Bartlett, P.L.: Self-distillation amplifies regularization in hilbert space. arXiv 2002.05715 (2020)"},{"key":"14_CR26","unstructured":"Ovadia, Y., Fertig, E., et\u00a0al., J.J.R.: Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift. In: NeurIPS 2019"},{"key":"14_CR27","unstructured":"Park, W., Kim, D., Lu, Y., Cho: Relational knowledge distillation. In: CVPR \u201919"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Pouromran, F., Radhakrishnan, S., Kamarthi, S.: Exploration of physiological sensors, features, and ml models for pain intensity estimation. PlusOne J. 16(7), e0254108 (2021)","DOI":"10.1371\/journal.pone.0254108"},{"key":"14_CR29","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: ICLR (2015)"},{"issue":"13","key":"14_CR30","doi-asserted-by":"publisher","first-page":"14875","DOI":"10.1609\/aaai.v38i13.29407","volume":"38","author":"P Sarkar","year":"2024","unstructured":"Sarkar, P., Etemad, A.: XKD: cross-modal knowledge distillation with domain alignment for video representation learning. AAAI 38(13), 14875\u201314885 (2024)","journal-title":"AAAI"},{"key":"14_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-09593-1_14","volume-title":"Tree-Based Models for Pain Detection from Biomedical Signals","author":"H Shi","year":"2022","unstructured":"Shi, H., Chikhaoui, B., Wang, S.: Tree-Based Models for Pain Detection from Biomedical Signals. Springer International Publishing, ICOST (2022)"},{"key":"14_CR32","unstructured":"Stanton, S., Izmailov, P., Kirichenko, P., Alemi, A.A., Wilson, A.G.: Does knowledge distillation really work? arXiv 2106.05945 (2021)"},{"key":"14_CR33","doi-asserted-by":"publisher","first-page":"4503","DOI":"10.3390\/s19204503","volume":"19","author":"P Thiam","year":"2019","unstructured":"Thiam, P., Bellmann, P., Kestler, H.A., Schwenker, F.: Exploring deep physiological models for nociceptive pain recognition. Sensors 19, 4503 (2019)","journal-title":"Sensors"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Thiam, P., Hihn, H., Braun, D.A., Kestler, H.A., Schwenker, F.: Multi-modal pain intensity assessment based on physiological signals. Front. Physiol. (2022)","DOI":"10.3389\/fphys.2021.720464"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Walter, S., Werner, E.A.: The biovid heat pain database: data for the advancement and systematic validation of an automated pain recognition. In: IEEE ICC (2013)","DOI":"10.1109\/CYBConf.2013.6617456"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Wang, R., Xu, K., Feng, H., Chen, W.: Hybrid RNN-ANN based deep physiological network for pain recognition. In: 42nd IEEE EMBC (2020)","DOI":"10.1109\/EMBC44109.2020.9175247"},{"key":"14_CR37","unstructured":"Werner, P., Al-Hamadi, A., Limbrecht-Ecklundt, K., Walter, S., Gruss, S., Traue, H.C.: Automatic pain assessment with facial activity descriptors. IEEE TAC 99, 1 (2016)"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Werner, P., Al-Hamadi, A., Niese, R., Walter, S., Gruss, S., Traue, H.C.: Automatic pain recognition from video and biomedical signals. In: ICPR (2014)","DOI":"10.1109\/ICPR.2014.784"},{"key":"14_CR39","unstructured":"Wortsman, M., Ilharco, G., Gadre, S.Y., et\u00a0al., R.R.: Model soups. arXiv 2203.05482 (2022)"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Yue, Z., Wang, Y., Duan, J., Yang, T., Huang, C., Tong, Y., Xu, B.: TS2Vec: towards universal representation of time series. In: AAAI (2021)","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"14_CR41","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of CNNs via attention transfer. arXiv 1612.03928 (2017)"},{"issue":"8","key":"14_CR42","first-page":"4388","volume":"44","author":"L Zhang","year":"2021","unstructured":"Zhang, L., Bao, C., Ma, K.: Self-distillation: towards efficient and compact neural networks. IEEE T-PAMI 44(8), 4388\u20134403 (2021)","journal-title":"IEEE T-PAMI"},{"key":"14_CR43","unstructured":"Zhang, Z., Sabuncu, M.R.: Self-distillation as instance-specific label smoothing 2006, 05065 (2020)"}],"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\/978-3-032-06106-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:04:35Z","timestamp":1782309875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"3 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}