{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:49:27Z","timestamp":1742914167242,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819947515"},{"type":"electronic","value":"9789819947522"}],"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\/978-981-99-4752-2_66","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T16:02:10Z","timestamp":1690732930000},"page":"804-816","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KDCE: Effective Lifelong Learning for Code Pre-train Language Model"],"prefix":"10.1007","author":[{"given":"Jiadong","family":"Feng","sequence":"first","affiliation":[]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"66_CR1","doi-asserted-by":"crossref","unstructured":"Niu, C., Li, C., Ng, V., et al.: Spt-code: sequence-to-sequence pre-training for learning the representation of source code. arXiv preprint arXiv:2201.01549 (2022)","DOI":"10.1145\/3510003.3510096"},{"key":"66_CR2","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, D., Tang, D., et al.: Codebert: a pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"66_CR3","unstructured":"Guo, D., Ren, S., Lu, S., et al.: Graphcodebert: pre-training code representations with data flow. arXiv preprint arXiv:2009.08366 (2020)"},{"key":"66_CR4","unstructured":"Sun, F.K., Ho, C.H., Lee, H.Y.: Lamol: language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329 (2019)"},{"issue":"12","key":"66_CR5","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3381831","volume":"63","author":"R Schwartz","year":"2020","unstructured":"Schwartz, R., Dodge, J., Smith, N.A., et al.: Green ai. Commun. ACM 63(12), 54\u201363 (2020)","journal-title":"Commun. ACM"},{"key":"66_CR6","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., et al.: icarl: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001\u20132010 (2017)","DOI":"10.1109\/CVPR.2017.587"},{"key":"66_CR7","unstructured":"Rolnick D, Ahuja A, Schwarz J, et al.: Experience replay for continual learning[J]. Advances in Neural Information Processing Systems, 2019, 32"},{"key":"66_CR8","unstructured":"Sun, F.K., Ho, C.H., Lee, H.Y.: Lamol.: language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329 (2019)"},{"key":"66_CR9","unstructured":"Lopez-Paz, D., Ranzato, M.A.: Gradient episodic memory for continual learning. Advances in neural information processing systems, 30 (2017)"},{"key":"66_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-030-01219-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Aljundi","year":"2018","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 144\u2013161. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_9"},{"key":"66_CR11","unstructured":"Schwarz, J., Czarnecki, W., Luketina, J., et al.: Progress & compress: A scalable framework for continual learning. In: International Conference on Machine Learning. PMLR, pp. 4528\u20134537 (2018)"},{"key":"66_CR12","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Marasovi\u0107, A., Swayamdipta, S., et al.: Don't stop pretraining: Adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964 (2020)","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"66_CR13","unstructured":"Yoon, J., Yang, E., Lee, J., et al.: Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547 (2017)"},{"key":"66_CR14","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"66_CR15","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"66_CR16","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"66_CR17","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"66_CR18","unstructured":"Clark, K.L., Le, M.T., Manning, Q.V., et al.: Pre-training text encoders as discriminators rather than generators. Preprint at https:\/\/arxiv.org\/abs\/2003.10555 (2020)"},{"key":"66_CR19","unstructured":"Buratti, L., Pujar, S., Bornea, M., et al.: Exploring software naturalness through neural language models. arXiv preprint arXiv:2006.12641 (2020)"},{"key":"66_CR20","unstructured":"Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: International conference on machine learning. PMLR, pp. 3987\u20133995 (2017)"},{"key":"66_CR21","unstructured":"Shin, H., Lee, J.K., Kim, J., et al.: Continual learning with deep generative replay. Advances in neural information processing systems, 30 (2017)"},{"key":"66_CR22","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning. PMLR, 2019, pp. 2790\u20132799"},{"key":"66_CR23","doi-asserted-by":"crossref","unstructured":"Chen, C., Yin, Y., Shang, L., et al.: bert2bert: towards reusable pretrained language models. arXiv preprint arXiv:2110.07143 (2021)","DOI":"10.18653\/v1\/2022.acl-long.151"},{"key":"66_CR24","doi-asserted-by":"crossref","unstructured":"Qin, Y., Zhang, J., Lin, Y., et al.: ELLE: efficient lifelong pre-training for emerging data. arXiv preprint arXiv:2203.06311 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.220"},{"key":"66_CR25","unstructured":"Gong, L., He, D., Li, Z., et al.: Efficient training of bert by progressively stacking. In: International Conference on Machine Learning. PMLR, pp. 2337\u20132346 (2019)"},{"key":"66_CR26","doi-asserted-by":"crossref","unstructured":"Sun, S., Cheng, Y., Gan, Z., et al.: Patient knowledge distillation for bert model compression. arXiv preprint arXiv:1908.09355 (2019)","DOI":"10.18653\/v1\/D19-1441"},{"key":"66_CR27","doi-asserted-by":"crossref","unstructured":"Jin, X., Zhang, D., Zhu, H., et al.: Lifelong pretraining: continually adapting language models to emerging corpora. arXiv preprint arXiv:2110.08534 (2021)","DOI":"10.18653\/v1\/2022.bigscience-1.1"},{"key":"66_CR28","unstructured":"Husain, H., Wu, H.H., Gazit, T., et al.: Codesearchnet challenge: evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436 (2019)"},{"key":"66_CR29","doi-asserted-by":"crossref","unstructured":"Hu, X., Li, G., Xia, X., et al.: Summarizing source code with transferred api knowledge (2018)","DOI":"10.24963\/ijcai.2018\/314"},{"key":"66_CR30","unstructured":"Barone, A.V.M., Sennrich, R.: A parallel corpus of python functions and documentation strings for automated code documentation and code generation. arXiv preprint arXiv:1707.02275 (2017)"},{"key":"66_CR31","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., et al.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"66_CR32","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"66_CR33","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Hovy, E.: Manual and automatic evaluation of summaries. In: Proceedings of the ACL-02 Workshop on Automatic Summarization, pp. 45\u201351 (2002)","DOI":"10.3115\/1118162.1118168"},{"key":"66_CR34","doi-asserted-by":"crossref","unstructured":"Cha, H., Lee, J., Shin, J.: Co2l: Contrastive continual learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9516\u20139525 (2021)","DOI":"10.1109\/ICCV48922.2021.00938"},{"key":"66_CR35","unstructured":"Hinton, G., Vinyals O, Dean J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"66_CR36","unstructured":"Kingma D P, Ba J.: Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014"},{"key":"66_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, X., et al.: Ddpnas: efficient neural architecture search via dynamic distribution pruning. Int. J. Comput. Vis., 1\u201316 (2023)","DOI":"10.1007\/s11263-023-01753-6"},{"key":"66_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, X., et al.: Migo-nas: towards fast and generalizable neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 2936\u20132952 (2021)","DOI":"10.1109\/TPAMI.2021.3065138"},{"key":"66_CR39","unstructured":"Zhang, S., et al.: You only compress once: towards effective and elastic BERT compression via exploit-explore stochastic nature gradient. arXiv preprint arXiv:2106.02435 (2021)"},{"key":"66_CR40","unstructured":"Zhang, S., et al.: Targeted hyperparameter optimization with lexicographic preferences over multiple objectives. In: The Eleventh International Conference on Learning Representations (2023)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4752-2_66","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T23:17:07Z","timestamp":1690931827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4752-2_66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947515","9789819947522"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4752-2_66","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":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}