{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:04:22Z","timestamp":1769731462083,"version":"3.49.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031109881","type":"print"},{"value":"9783031109898","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-10989-8_54","type":"book-chapter","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T22:30:36Z","timestamp":1658183436000},"page":"681-692","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Classification of\u00a0Heads in\u00a0Multi-head Attention Mechanisms"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3626-9792","authenticated-orcid":false,"given":"Feihu","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3258-3354","authenticated-orcid":false,"given":"Min","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7211-6991","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7302-2655","authenticated-orcid":false,"given":"Dian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8281-0458","authenticated-orcid":false,"given":"Zimeng","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"54_CR1","doi-asserted-by":"crossref","unstructured":"Correia, G.M., Niculae, V., Martins, A.F.: Adaptively sparse transformers. arXiv preprint arXiv:1909.00015 (2019)","DOI":"10.18653\/v1\/D19-1223"},{"key":"54_CR2","unstructured":"Devlin, J., Chang, M.W., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv e-prints arXiv:1810.04805, October 2018. https:\/\/ui.adsabs.harvard.edu\/abs\/2018arXiv181004805D"},{"key":"54_CR3","unstructured":"Dosovitskiy, A., Beyer, L., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th ICLR (2021)"},{"key":"54_CR4","doi-asserted-by":"crossref","unstructured":"Elliott, D., Frank, S., Sima\u2019an, K., Specia, L.: Multi30k: multilingual English-German image descriptions. arXiv preprint arXiv:1605.00459 (2016)","DOI":"10.18653\/v1\/W16-3210"},{"key":"54_CR5","unstructured":"Huang, L., Yuan, Y., Guo, J., Zhang, C., Chen, X., Wang, J.: Interlaced sparse self-attention for semantic segmentation. arXiv preprint arXiv:1907.12273 (2019)"},{"key":"54_CR6","unstructured":"Kawakami, K.: Supervised sequence labelling with recurrent neural networks. Ph.D. thesis (2008)"},{"key":"54_CR7","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"issue":"4","key":"54_CR8","first-page":"2833","volume":"17","author":"Y Li","year":"2021","unstructured":"Li, Y., Song, Y., et al.: Intelligent fault diagnosis by fusing domain adversarial training and maximum mean discrepancy via ensemble learning. IEEE TII 17(4), 2833\u20132841 (2021)","journal-title":"IEEE TII"},{"key":"54_CR9","unstructured":"Liu, M., Zhang, S., et al.: H infinite state estimation for discrete-time chaotic systems based on a unified model. IEEE Trans. SMC (B) (2012)"},{"key":"54_CR10","first-page":"316","volume":"118","author":"Z Lu","year":"2018","unstructured":"Lu, Z., Wang, N., et al.: IoTDeM: an IoT big data-oriented MapReduce performance prediction extended model in multiple edge clouds. JPDC 118, 316\u2013327 (2018)","journal-title":"JPDC"},{"key":"54_CR11","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"54_CR12","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.inffus.2019.07.012","volume":"55","author":"H Qiu","year":"2020","unstructured":"Qiu, H., Qiu, M., Lu, Z.: Selective encryption on ECG data in body sensor network based on supervised machine learning. Infor. Fusion 55, 59\u201367 (2020)","journal-title":"Infor. Fusion"},{"issue":"3","key":"54_CR13","first-page":"2124","volume":"17","author":"H Qiu","year":"2020","unstructured":"Qiu, H., Zheng, Q., et al.: Deep residual learning-based enhanced JPEG compression in the internet of things. IEEE TII 17(3), 2124\u20132133 (2020)","journal-title":"IEEE TII"},{"issue":"7","key":"54_CR14","first-page":"4560","volume":"22","author":"H Qiu","year":"2021","unstructured":"Qiu, H., Zheng, Q., et al.: Topological graph convolutional network-based urban traffic flow and density prediction. IEEE TITS 22(7), 4560\u20134569 (2021)","journal-title":"IEEE TITS"},{"key":"54_CR15","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1016\/j.future.2017.08.004","volume":"87","author":"M Qiu","year":"2018","unstructured":"Qiu, M., Gai, K., Xiong, Z.: Privacy-preserving wireless communications using bipartite matching in social big data. FGCS 87, 772\u2013781 (2018)","journal-title":"FGCS"},{"key":"54_CR16","doi-asserted-by":"crossref","unstructured":"Qiu, M., Liu, J., et al.: A novel energy-aware fault tolerance mechanism for wireless sensor networks. In: IEEE\/ACM Conference, GCC (2011)","DOI":"10.1109\/GreenCom.2011.18"},{"key":"54_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, M., Xue, C., et al.: Energy minimization with soft real-time and DVS for uniprocessor and multiprocessor embedded systems. In: IEEE DATE Conference, pp. 1\u20136 (2007)","DOI":"10.1109\/DATE.2007.364537"},{"key":"54_CR18","unstructured":"Shazeer, N., Lan, Z., Cheng, Y., Ding, N., Hou, L.: Talking-heads attention. arXiv preprint arXiv:2003.02436 (2020)"},{"key":"54_CR19","doi-asserted-by":"crossref","unstructured":"Tang, G., Nivre, J.: An analysis of attention mechanisms: the case of word sense disambiguation in neural machine translation. In: 3rd Conference on Machine Translation (2018)","DOI":"10.18653\/v1\/W18-6304"},{"key":"54_CR20","unstructured":"Vaswani, A., Shazeer, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"54_CR21","doi-asserted-by":"crossref","unstructured":"Voita, E., Serdyukov, P., Sennrich, R., Titov, I.: Context-aware neural machine translation learns anaphora resolution. arXiv e-prints arXiv:1805.10163, May 2018. https:\/\/ui.adsabs.harvard.edu\/abs\/2018arXiv180510163V","DOI":"10.18653\/v1\/P18-1117"},{"key":"54_CR22","doi-asserted-by":"publisher","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned (2019). https:\/\/doi.org\/10.18653\/v1\/p19-1580","DOI":"10.18653\/v1\/p19-1580"},{"issue":"3","key":"54_CR23","first-page":"330","volume":"73","author":"G Wu","year":"2013","unstructured":"Wu, G., Zhang, H., et al.: A decentralized approach for mining event correlations in distributed system monitoring. JPDC 73(3), 330\u2013340 (2013)","journal-title":"JPDC"},{"key":"54_CR24","unstructured":"Zaheer, M., Guruganesh, G., et al.: Big bird: transformers for longer sequences (2021)"},{"key":"54_CR25","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. CoRR abs\/1409.2329 (2014). http:\/\/arxiv.org\/abs\/1409.2329"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-10989-8_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T22:46:02Z","timestamp":1658184362000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-10989-8_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031109881","9783031109898"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-10989-8_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem22.smart-conf.net\/index.html","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":"498","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":"169","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":"0","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":"34% - 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":"3","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":"10","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)"}}]}}