{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T02:51:03Z","timestamp":1776221463501,"version":"3.50.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319712482","type":"print"},{"value":"9783319712499","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-71249-9_12","type":"book-chapter","created":{"date-parts":[[2017,12,29]],"date-time":"2017-12-29T08:53:43Z","timestamp":1514537623000},"page":"187-202","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Ensemble-Compression: A New Method for Parallel Training of Deep Neural Networks"],"prefix":"10.1007","author":[{"given":"Shizhao","family":"Sun","sequence":"first","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[]},{"given":"Xiaoguang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,30]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bucilua, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM Conference on Knowledge Discovery and Data Mining, pp. 535\u2013541. ACM (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"12_CR2","unstructured":"Chen, J., Monga, R., Bengio, S., Jozefowicz, R.: Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981 (2016)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chen, K., Huo, Q.: Scalable training of deep learning machines by incremental block training with intra-block parallel optimization and blockwise model-update filtering. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5880\u20135884. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"12_CR4","unstructured":"Chen, W., Wilson, J.T., Tyree, S., Weinberger, K.Q., Chen, Y.: Compressing neural networks with the hashing trick. In: Proceedings of the 32st International Conference on Machine Learning (2015)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642\u20133649. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"12_CR6","unstructured":"Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Mao, M., Senior, A., Tucker, P., Yang, K., Le, Q.V., et al.: Large scale distributed deep networks. In: Advances in Neural Information Processing Systems, pp. 1223\u20131231 (2012)"},{"issue":"1","key":"12_CR7","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"12_CR8","unstructured":"Denil, M., Shakibi, B., Dinh, L., de Freitas, N., et al.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems, pp. 2148\u20132156 (2013)"},{"key":"12_CR9","unstructured":"Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269\u20131277 (2014)"},{"key":"12_CR10","unstructured":"Gong, Y., Liu, L., Yang, M., Bourdev, L.: Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)"},{"key":"12_CR11","first-page":"1135","volume":"28","author":"S Han","year":"2015","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28, 1135\u20131143 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"12_CR12","first-page":"820","volume":"29","author":"D He","year":"2016","unstructured":"He, D., Xia, Y., Qin, T., Wang, L., Yu, N., Liu, T., Ma, W.Y.: Dual learning for machine translation. Adv. Neural Inf. Process. Syst. 29, 820\u2013828 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"12_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"12_CR16","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. University of Toronto, Technical report (2009)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Kuncheva, L., Whitaker, C.: Measures of diversity in classifier ensembles. In: Machine Learning, pp. 181\u2013207 (2003)","DOI":"10.1023\/A:1022859003006"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Andersen, D.G., Park, J.W., Smola, A.J., Ahmed, A., Josifovski, V., Long, J., Shekita, E.J., Su, B.Y.: Scaling distributed machine learning with the parameter server. In: 11th USENIX Symposium on Operating Systems Design and Implementation, pp. 583\u2013598 (2014)","DOI":"10.1145\/2640087.2644155"},{"key":"12_CR19","unstructured":"Min, L., Qiang, C., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2014)"},{"key":"12_CR20","unstructured":"Povey, D., Zhang, X., Khudanpur, S.: Parallel training of DNNs with natural gradient and parameter averaging. arXiv preprint arXiv:1410.7455 (2014)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Rigamonti, R., Sironi, A., Lepetit, V., Fua, P.: Learning separable filters. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2754\u20132761. IEEE (2013)","DOI":"10.1109\/CVPR.2013.355"},{"key":"12_CR22","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"issue":"3","key":"12_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"12_CR24","first-page":"190","volume":"8","author":"P Sollich","year":"1996","unstructured":"Sollich, P., Krogh, A.: Learning with ensembles: how overfitting can be useful. Adv. Neural Inf. Process. Syst. 8, 190\u2013196 (1996)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. arXiv preprint arXiv:1409.4842 (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"12_CR26","first-page":"685","volume":"28","author":"S Zhang","year":"2015","unstructured":"Zhang, S., Choromanska, A.E., LeCun, Y.: Deep learning with elastic averaging SGD. Adv. Neural Inf. Process. Syst. 28, 685\u2013693 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, X., Trmal, J., Povey, D., Khudanpur, S.: Improving deep neural network acoustic models using generalized maxout networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 215\u2013219. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853589"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-71249-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T08:31:18Z","timestamp":1693384278000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-71249-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319712482","9783319712499"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-71249-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"30 December 2017","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":"Skopje","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macedonia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2017.ijs.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}