{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T01:29:28Z","timestamp":1782178168044,"version":"3.54.5"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031703584","type":"print"},{"value":"9783031703591","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70359-1_1","type":"book-chapter","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T04:02:43Z","timestamp":1724904163000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Model Fusion via\u00a0Neuron Transplantation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4337-407X","authenticated-orcid":false,"given":"Muhammed","family":"\u00d6z","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1454-4144","authenticated-orcid":false,"given":"Nicholas","family":"Kiefer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7156-2022","authenticated-orcid":false,"given":"Charlotte","family":"Debus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasmin","family":"H\u00f6rter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5065-469X","authenticated-orcid":false,"given":"Achim","family":"Streit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2233-1041","authenticated-orcid":false,"given":"Markus","family":"G\u00f6tz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","unstructured":"Ainsworth, S.K., Hayase, J., Srinivasa, S.: Git re-basin: merging models modulo permutation symmetries (2023). https:\/\/doi.org\/10.48550\/arXiv.2209.04836","DOI":"10.48550\/arXiv.2209.04836"},{"key":"1_CR2","unstructured":"Allen-Zhu, Z., Li, Y.: Towards understanding ensemble, knowledge distillation and self-distillation in deep learning. CoRR abs\/2012.09816 (2020). https:\/\/arxiv.org\/abs\/2012.09816"},{"key":"1_CR3","doi-asserted-by":"publisher","unstructured":"Anwar, S., Hwang, K., Sung, W.: Structured pruning of deep convolutional neural networks. J. Emerg. Technol. Comput. Syst. 13(3) (2017). https:\/\/doi.org\/10.1145\/3005348","DOI":"10.1145\/3005348"},{"key":"1_CR4","doi-asserted-by":"publisher","unstructured":"Bhagat\u00a0Smith, J., Gashler, M.: Investigation of how neural networks learn from the experiences of peers through periodic weight averaging. In: 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA) (2017). https:\/\/doi.org\/10.1109\/ICMLA.2017.00-72","DOI":"10.1109\/ICMLA.2017.00-72"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with pathways (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.02311","DOI":"10.48550\/arXiv.2204.02311"},{"key":"1_CR6","doi-asserted-by":"publisher","unstructured":"Das, D., et al.: Distributed deep learning using synchronous stochastic gradient descent (2016). https:\/\/doi.org\/10.48550\/arXiv.1602.06709","DOI":"10.48550\/arXiv.1602.06709"},{"issue":"6","key":"1_CR7","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2211477","journal-title":"IEEE Signal Process. Mag."},{"key":"1_CR8","doi-asserted-by":"publisher","unstructured":"Dong, X., Yu, Z., Cao, W., Shi, Y., Ma, Q.: A survey on ensemble learning. Front. Comput. Sci. 14(2), 241\u2013258 (2020). https:\/\/doi.org\/10.1007\/s11704-019-8208-z","DOI":"10.1007\/s11704-019-8208-z"},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"Entezari, R., Sedghi, H., Saukh, O., Neyshabur, B.: The role of permutation invariance in linear mode connectivity of neural networks (2022). https:\/\/doi.org\/10.48550\/arXiv.2110.06296","DOI":"10.48550\/arXiv.2110.06296"},{"key":"1_CR10","doi-asserted-by":"publisher","unstructured":"Fang, G., Ma, X., Song, M., Mi, M.B., Wang, X.: Depgraph: towards any structural pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16091\u201316101 (2023). https:\/\/doi.org\/10.48550\/arXiv.2301.12900","DOI":"10.48550\/arXiv.2301.12900"},{"key":"1_CR11","unstructured":"Flamary, R., et al.: Pot: python optimal transport. J. Mach. Learn. Res. 22(78), 1\u20138 (2021). http:\/\/jmlr.org\/papers\/v22\/20-451.html"},{"key":"1_CR12","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). https:\/\/doi.org\/10.48550\/arXiv.1503.02531","DOI":"10.48550\/arXiv.1503.02531"},{"key":"1_CR14","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs\/1502.03167 (2015). http:\/\/arxiv.org\/abs\/1502.03167"},{"key":"1_CR15","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. University of Toronto (2012)"},{"issue":"11","key":"1_CR16","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"issue":"1","key":"1_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11063-019-10074-0","volume":"51","author":"MI Leontev","year":"2019","unstructured":"Leontev, M.I., Islenteva, V., Sukhov, S.V.: Non-iterative knowledge fusion in deep convolutional neural networks. Neural Process. Lett. 51(1), 1\u201322 (2019). https:\/\/doi.org\/10.1007\/s11063-019-10074-0","journal-title":"Neural Process. Lett."},{"key":"1_CR18","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=rJqFGTslg"},{"key":"1_CR19","doi-asserted-by":"publisher","unstructured":"Li, W., Peng, Y., Zhang, M., Ding, L., Hu, H., Shen, L.: Deep model fusion: a survey (2023). https:\/\/doi.org\/10.48550\/arXiv.2309.15698","DOI":"10.48550\/arXiv.2309.15698"},{"key":"1_CR20","doi-asserted-by":"publisher","unstructured":"Liebenwein, L., Baykal, C., Carter, B., Gifford, D., Rus, D.: Lost in pruning: the effects of pruning neural networks beyond test accuracy (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.03014","DOI":"10.48550\/arXiv.2103.03014"},{"key":"1_CR21","unstructured":"Liu, C., Lou, C., Wang, R., Xi, A.Y., Shen, L., Yan, J.: Deep neural network fusion via graph matching with applications to model ensemble and federated learning. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 13857\u201313869. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/liu22k.html"},{"key":"1_CR22","doi-asserted-by":"publisher","unstructured":"Mishra, R., Gupta, H.P., Dutta, T.: A survey on deep neural network compression: challenges, overview, and solutions (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.03954","DOI":"10.48550\/arXiv.2010.03954"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Mohammed, A., Kora, R.: A comprehensive review on ensemble deep learning: opportunities and challenges. J. King Saud Univ. Comput. Inf. Sci. 35(2), 757\u2013774 (2023). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1319157823000228","DOI":"10.1016\/j.jksuci.2023.01.014"},{"key":"1_CR24","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.: Reading digits in natural images with unsupervised feature learning. In: NIPS (2011)"},{"key":"1_CR25","unstructured":"Neyshabur, B., Sedghi, H., Zhang, C.: What is being transferred in transfer learning? CoRR abs\/2008.11687 (2020). https:\/\/arxiv.org\/abs\/2008.11687"},{"key":"1_CR26","unstructured":"Vingelmann, P., Fitzek, F.H.: Cuda, release: 10.2.89. NVIDIA (2020). https:\/\/developer.nvidia.com\/cuda-toolkit"},{"key":"1_CR27","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Qi, P., Chiaro, D., Guzzo, A., Ianni, M., Fortino, G., Piccialli, F.: Model aggregation techniques in federated learning: a comprehensive survey. Future Gener. Comput. Syst. 150, 272\u2013293 (2024). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167739X23003333","DOI":"10.1016\/j.future.2023.09.008"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Qian, C., Yu, Y., Zhou, Z.H.: Pareto ensemble pruning. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI 2015, pp. 2935\u20132941. AAAI Press (2015)","DOI":"10.1609\/aaai.v29i1.9579"},{"issue":"5","key":"1_CR30","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/72.248452","volume":"4","author":"R Reed","year":"1993","unstructured":"Reed, R.: Pruning algorithms-a survey. IEEE Trans. Neural Networks 4(5), 740\u2013747 (1993). https:\/\/doi.org\/10.1109\/72.248452","journal-title":"IEEE Trans. Neural Networks"},{"key":"1_CR31","unstructured":"Shen, Z., He, Z., Xue, X.: MEAL: multi-model ensemble via adversarial learning. CoRR abs\/1812.02425 (2018). http:\/\/arxiv.org\/abs\/1812.02425"},{"key":"1_CR32","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015). https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"1_CR33","doi-asserted-by":"publisher","unstructured":"Singh, S.P., Jaggi, M.: Model fusion via optimal transport (2023). https:\/\/doi.org\/10.48550\/arXiv.1910.05653","DOI":"10.48550\/arXiv.1910.05653"},{"key":"1_CR34","doi-asserted-by":"publisher","unstructured":"Sun, S., Chen, W., Bian, J., Liu, X., Liu, T.Y.: Ensemble-compression: a new method for parallel training of deep neural networks (2017). https:\/\/doi.org\/10.48550\/arXiv.1606.00575","DOI":"10.48550\/arXiv.1606.00575"},{"key":"1_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR abs\/1706.03762 (2017). http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"1_CR36","unstructured":"Walawalkar, D., Shen, Z., Savvides, M.: Online ensemble model compression using knowledge distillation. CoRR abs\/2011.07449 (2020). https:\/\/arxiv.org\/abs\/2011.07449"},{"key":"1_CR37","unstructured":"Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D.S., Khazaeni, Y.: Federated learning with matched averaging. CoRR abs\/2002.06440 (2020). https:\/\/arxiv.org\/abs\/2002.06440"},{"key":"1_CR38","doi-asserted-by":"publisher","unstructured":"Wortsman, M., et al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.05482","DOI":"10.48550\/arXiv.2203.05482"},{"key":"1_CR39","doi-asserted-by":"publisher","unstructured":"Yang, Y., Lv, H.: Discussion of ensemble learning under the era of deep learning. CoRR abs\/2101.08387 (2021). https:\/\/doi.org\/10.1007\/s10462-022-10283-5. https:\/\/arxiv.org\/abs\/2101.08387","DOI":"10.1007\/s10462-022-10283-5"}],"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\/978-3-031-70359-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:27:27Z","timestamp":1768202847000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70359-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703584","9783031703591"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70359-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","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":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}