{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:45:42Z","timestamp":1743043542737,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031637483"},{"type":"electronic","value":"9783031637490"}],"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\/978-3-031-63749-0_13","type":"book-chapter","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T19:21:12Z","timestamp":1719516072000},"page":"181-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Data-Efficient Knowledge Distillation with\u00a0Teacher Assistant-Based Dynamic Objective Alignment"],"prefix":"10.1007","author":[{"given":"Yangyan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangfang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongxin","family":"Mi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dakui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Majing","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,28]]},"reference":[{"unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)","key":"13_CR1"},{"unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)","key":"13_CR2"},{"doi-asserted-by":"crossref","unstructured":"Li, L., et al.: From mimicking to integrating: knowledge integration for pre-trained language models. In: EMNLP, pp. 6391\u20136402 (2022)","key":"13_CR3","DOI":"10.18653\/v1\/2022.findings-emnlp.477"},{"unstructured":"Li, Z., Xu, X., Shen, T., Xu, C., Gu, J.C., Tao, C.: Leveraging large language models for NLG evaluation: a survey. arXiv preprint arXiv:2401.07103 (2024)","key":"13_CR4"},{"unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)","key":"13_CR5"},{"doi-asserted-by":"crossref","unstructured":"Luo, S., Wang, X., Fang, G., Hu, Y., Tao, D., Song, M.: Knowledge amalgamation from heterogeneous networks by common feature learning. In: IJCAI, pp. 3087\u20133093 (2019)","key":"13_CR6","DOI":"10.24963\/ijcai.2019\/428"},{"unstructured":"Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: ACL, pp. 142\u2013150 (2011)","key":"13_CR7"},{"unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)","key":"13_CR8"},{"unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)","key":"13_CR9"},{"unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)","key":"13_CR10"},{"doi-asserted-by":"crossref","unstructured":"Saravia, E., Liu, H.T., Huang, Y., Wu, J., Chen, Y.: CARER: contextualized affect representations for emotion recognition. In: EMNLP, pp. 3687\u20133697 (2018)","key":"13_CR11","DOI":"10.18653\/v1\/D18-1404"},{"doi-asserted-by":"crossref","unstructured":"Shen, C., Wang, X., Song, J., Sun, L., Song, M.: Amalgamating knowledge towards comprehensive classification. In: AAAI, pp. 3068\u20133075 (2019)","key":"13_CR12","DOI":"10.1609\/aaai.v33i01.33013068"},{"doi-asserted-by":"crossref","unstructured":"Sun, S., Cheng, Y., Gan, Z., Liu, J.: Patient knowledge distillation for BERT model compression. In: ACL\/IJCNLP, pp. 4322\u20134331 (2019)","key":"13_CR13","DOI":"10.18653\/v1\/D19-1441"},{"unstructured":"Turc, I., Chang, M., Lee, K., Toutanova, K.: Well-read students learn better: the impact of student initialization on knowledge distillation. arXiv preprint arXiv:1908.08962 (2019)","key":"13_CR14"},{"doi-asserted-by":"crossref","unstructured":"Vongkulbhisal, J., Vinayavekhin, P., Scarzanella, M.V.: Unifying heterogeneous classifiers with distillation. In: CVPR, pp. 3175\u20133184 (2019)","key":"13_CR15","DOI":"10.1109\/CVPR.2019.00329"},{"doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: ICLR (2019)","key":"13_CR16","DOI":"10.18653\/v1\/W18-5446"},{"doi-asserted-by":"crossref","unstructured":"Wang, C., Lu, Y., Mu, Y., Hu, Y., Xiao, T., Zhu, J.: Improved knowledge distillation for pre-trained language models via knowledge selection. arXiv preprint arXiv:2302.00444 (2023)","key":"13_CR17","DOI":"10.18653\/v1\/2022.findings-emnlp.464"},{"doi-asserted-by":"crossref","unstructured":"Wang, W., Bao, H., Huang, S., Dong, L., Wei, F.: Minilmv2: multi-head self-attention relation distillation for compressing pretrained transformers. In: ACL\/IJCNLP, pp. 2140\u20132151 (2021)","key":"13_CR18","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"doi-asserted-by":"crossref","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: Minilm: deep self-attention distillation for task-agnostic compression of pre-trained transformers. In: NeurIPS (2020)","key":"13_CR19","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: EMNLP, pp. 38\u201345 (2020)","key":"13_CR20"},{"key":"13_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109338","volume":"138","author":"G Xu","year":"2023","unstructured":"Xu, G., Liu, Z., Loy, C.C.: Computation-efficient knowledge distillation via uncertainty-aware mixup. Pattern Recogn. 138, 109338 (2023)","journal-title":"Pattern Recogn."},{"key":"13_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/978-3-031-35995-8_39","volume-title":"Computational Science - ICCS 2023","author":"Y Xu","year":"2023","unstructured":"Xu, Y., Yuan, F., Cao, C., Su, M., Lu, Y., Liu, Y.: A contrastive self-distillation BERT with kernel alignment-based inference. In: Mikyska, J., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds.) ICCS 2023. LNCS, vol. 14073, pp. 553\u2013565. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-35995-8_39"},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: MetaBERT: collaborative meta-learning for accelerating BERT inference. In: CSCWD, pp. 119\u2013124. IEEE (2023)","key":"13_CR23","DOI":"10.1109\/CSCWD57460.2023.10152853"},{"unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J.G., Salakhutdinov, R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: NeurIPS, pp. 5754\u20135764 (2019)","key":"13_CR24"},{"doi-asserted-by":"crossref","unstructured":"Yuan, F., et al.: Reinforced multi-teacher selection for knowledge distillation. In: AAAI, pp. 14284\u201314291 (2021)","key":"13_CR25","DOI":"10.1609\/aaai.v35i16.17680"},{"unstructured":"Zhang, X., Zhao, J.J., LeCun, Y.: Character-level convolutional networks for text classification. In: NeurIPS, pp. 649\u2013657 (2015)","key":"13_CR26"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-63749-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T19:25:30Z","timestamp":1719516330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-63749-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031637483","9783031637490"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-63749-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 June 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malaga","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"2 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 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":"iccs-computsci2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}