{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:56:34Z","timestamp":1743022594834,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031359941"},{"type":"electronic","value":"9783031359958"}],"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\/978-3-031-35995-8_39","type":"book-chapter","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T07:02:24Z","timestamp":1687935744000},"page":"553-565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Contrastive Self-distillation BERT with\u00a0Kernel Alignment-Based Inference"],"prefix":"10.1007","author":[{"given":"Yangyan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangfang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Majing","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhai","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,26]]},"reference":[{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, pp. 4171\u20134186 (2019)","key":"39_CR1"},{"unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training. OpenAI (2018)","key":"39_CR2"},{"unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J.G., Salakhutdinov, R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS, pp. 5754\u20135764 (2019)","key":"39_CR3"},{"unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)","key":"39_CR4"},{"unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: International Conference on Learning Representations, ICLR (2020)","key":"39_CR5"},{"unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)","key":"39_CR6"},{"unstructured":"Tang, H., Zhang, X., Liu, K., Zhu, J., Kang, Z.: MKQ-BERT: quantized BERT with 4-bits weights and activations. arXiv preprint arXiv:2203.13483 (2022)","key":"39_CR7"},{"doi-asserted-by":"crossref","unstructured":"Lassance, C., Maachou, M., Park, J., Clinchant, S.: Learned token pruning in contextualized late interaction over BERT (colbert). In: SIGIR 2022: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2232\u20132236 (2022)","key":"39_CR8","DOI":"10.1145\/3477495.3531835"},{"unstructured":"Zhou, W., Xu, C., Ge, T., McAuley, J.J., Xu, K., Wei, F.: BERT loses patience: fast and robust inference with early exit. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS (2020)","key":"39_CR9"},{"doi-asserted-by":"crossref","unstructured":"Xin, J., Tang, R., Lee, J., Yu, Y., Lin, J.: DeeBERT: dynamic early exiting for accelerating BERT inference. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL, pp. 2246\u20132251 (2020)","key":"39_CR10","DOI":"10.18653\/v1\/2020.acl-main.204"},{"doi-asserted-by":"crossref","unstructured":"Liu, W., Zhou, P., Wang, Z., Zhao, Z., Deng, H., Ju, Q.: Fastbert: a self-distilling bert with adaptive inference time. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL, pp. 6035\u20136044 (2020)","key":"39_CR11","DOI":"10.18653\/v1\/2020.acl-main.537"},{"doi-asserted-by":"crossref","unstructured":"Zhu, W., Wang, X., Ni, Y., Xie, G.: GAML-BERT: improving BERT early exiting by gradient aligned mutual learning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 3033\u20133044 (2021)","key":"39_CR12","DOI":"10.18653\/v1\/2021.emnlp-main.242"},{"key":"39_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/978-3-030-88480-2_18","volume-title":"Natural Language Processing and Chinese Computing","author":"J Kong","year":"2021","unstructured":"Kong, J., Wang, J., Zhang, X.: Accelerating pretrained language model inference using weighted ensemble self-distillation. In: Wang, L., Feng, Y., Hong, Yu., He, R. (eds.) NLPCC 2021. LNCS (LNAI), vol. 13028, pp. 224\u2013235. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88480-2_18"},{"unstructured":"Kong, J., Wang, J., Yu, L., Zhang, X.: Accelerating inference for pretrained language models by unified multi-perspective early exiting. In: Proceedings of the 29th International Conference on Computational Linguistics, COLING, pp. 4677\u20134686 (2022)","key":"39_CR14"},{"doi-asserted-by":"crossref","unstructured":"Zhu, W.: Leebert: learned early exit for BERT with cross-level optimization. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP, pp. 2968\u20132980 (2021)","key":"39_CR15","DOI":"10.18653\/v1\/2021.acl-long.231"},{"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":"39_CR16"},{"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: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS (2020)","key":"39_CR17"},{"doi-asserted-by":"crossref","unstructured":"Xu, C., Zhou, W., Ge, T., Wei, F., Zhou, M.: BERT-of-theseus: compressing BERT by progressive module replacing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 7859\u20137869 (2020)","key":"39_CR18","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"issue":"11","key":"39_CR19","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1007\/s10115-022-01736-y","volume":"64","author":"M Ryu","year":"2022","unstructured":"Ryu, M., Lee, G., Lee, K.: Knowledge distillation for BERT unsupervised domain adaptation. Knowl. Inf. Syst. 64(11), 3113\u20133128 (2022)","journal-title":"Knowl. Inf. Syst."},{"doi-asserted-by":"crossref","unstructured":"Yao, S., Tan, J., Chen, X., Zhang, J., Zeng, X., Yang, K.: ReprBERT: distilling BERT to an efficient representation-based relevance model for e-commerce. In: KDD 2022: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4363\u20134371 (2022)","key":"39_CR20","DOI":"10.1145\/3534678.3539090"},{"doi-asserted-by":"crossref","unstructured":"Gao, Y., Zhang, B., Qi, X., So, H.K.: DPACS: hardware accelerated dynamic neural network pruning through algorithm-architecture co-design. In: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 2, ASPLOS, pp. 237\u2013251 (2023)","key":"39_CR21","DOI":"10.1145\/3575693.3575728"},{"doi-asserted-by":"crossref","unstructured":"Yuan, F., et al.: Reinforced multi-teacher selection for knowledge distillation. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI, pp. 14284\u201314291 (2021)","key":"39_CR22","DOI":"10.1609\/aaai.v35i16.17680"},{"doi-asserted-by":"crossref","unstructured":"Zhou, W., Xu, C., McAuley, J.J.: BERT learns to teach: knowledge distillation with meta learning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, ACL, pp. 7037\u20137049 (2022)","key":"39_CR23","DOI":"10.18653\/v1\/2022.acl-long.485"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhu, W., Zhang, J., Wang, P., Jin, R., Chung, T.: PCEE-BERT: accelerating BERT inference via patient and confident early exiting. In: Findings of the Association for Computational Linguistics: NAACL, pp. 327\u2013338 (2022)","key":"39_CR24","DOI":"10.18653\/v1\/2022.findings-naacl.25"},{"doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.T.: Branchynet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2464\u20132469. IEEE (2016)","key":"39_CR25","DOI":"10.1109\/ICPR.2016.7900006"},{"unstructured":"Kaya, Y., Hong, S., Dumitras, T.: Shallow-deep networks: understanding and mitigating network overthinking. In: Proceedings of the 36th International Conference on Machine Learning, ICML, vol. 97, pp. 3301\u20133310 (2019)","key":"39_CR26"},{"unstructured":"Elbayad, M., Gu, J., Grave, E., Auli, M.: Depth-adaptive transformer. arXiv preprint arXiv:1910.10073 (2019)","key":"39_CR27"},{"doi-asserted-by":"crossref","unstructured":"Schwartz, R., Stanovsky, G., Swayamdipta, S., Dodge, J., Smith, N.A.: The right tool for the job: matching model and instance complexities. arXiv preprint arXiv:2004.07453 (2020)","key":"39_CR28","DOI":"10.18653\/v1\/2020.acl-main.593"},{"doi-asserted-by":"crossref","unstructured":"Xin, J., Tang, R., Yu, Y., Lin, J.: BERxiT: early exiting for BERT with better fine-tuning and extension to regression. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL, pp. 91\u2013104 (2021)","key":"39_CR29","DOI":"10.18653\/v1\/2021.eacl-main.8"},{"doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Cascadebert: accelerating inference of pre-trained language models via calibrated complete models cascade. In: Findings of the Association for Computational Linguistics: EMNLP, pp. 475\u2013486 (2021)","key":"39_CR30","DOI":"10.18653\/v1\/2021.findings-emnlp.43"},{"unstructured":"Atito, S., Awais, M., Kittler, J.: Sit: Self-supervised vision transformer. arXiv preprint arXiv:2104.03602 (2021)","key":"39_CR31"},{"unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning, ICML, vol. 119, pp. 1597\u20131607 (2020)","key":"39_CR32"},{"unstructured":"Kornblith, S., Norouzi, M., Lee, H., Hinton, G.E.: Similarity of neural network representations revisited. In: Proceedings of the 36th International Conference on Machine Learning, ICML, vol. 97, pp. 3519\u20133529 (2019)","key":"39_CR33"},{"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. arXiv preprint arXiv:1804.07461 (2018)","key":"39_CR34","DOI":"10.18653\/v1\/W18-5446"},{"unstructured":"Liu, X., et al.: Towards efficient NLP: a standard evaluation and a strong baseline. arXiv preprint arXiv:2110.07038 (2021)","key":"39_CR35"},{"unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing transformer depth on demand with structured dropout. In: International Conference on Learning Representations, ICLR (2019)","key":"39_CR36"},{"doi-asserted-by":"crossref","unstructured":"Sun, S., Cheng, Y., Gan, Z., Liu, J.: Patient knowledge distillation for BERT model compression. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP, pp. 4322\u20134331 (2019)","key":"39_CR37","DOI":"10.18653\/v1\/D19-1441"},{"doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 38\u201345 (2020)","key":"39_CR38","DOI":"10.18653\/v1\/2020.emnlp-demos.6"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-35995-8_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T14:07:34Z","timestamp":1691071654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-35995-8_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031359941","9783031359958"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-35995-8_39","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":"26 June 2023","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":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"3 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 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":"iccs-computsci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"530","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":"188","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":"94","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":"35% - 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":"2,8","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":"3,2","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)"}}]}}