{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T07:07:43Z","timestamp":1783840063485,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228669","type":"print"},{"value":"9789819228645","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-2864-5_3","type":"book-chapter","created":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T06:21:47Z","timestamp":1783837307000},"page":"24-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reducing Redundancy in\u00a0Multi-Head Attention via\u00a0Diversity Regularization"],"prefix":"10.1007","author":[{"given":"Kejie","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"3_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference On Learning Representations (2020)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR4","unstructured":"Huang, Z., et al.: Ultra-sparse memory network. In: The Thirteenth International Conference On Learning Representations, ICLR 2025, Singapore, 24\u201328 April 2025 (2025)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: VQ-LLM: high-performance code generation for vector quantization augmented LLM inference. In: 2025 IEEE International Symposium On High Performance Computer Architecture (HPCA), pp. 1496\u20131509 (2025)","DOI":"10.1109\/HPCA61900.2025.00112"},{"key":"3_CR6","unstructured":"Agarwal, S., et al.: CHAI: clustered head attention for efficient LLM inference. In: International Conference on Machine Learning, pp. 291\u2013312 (2024)"},{"key":"3_CR7","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one?. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"3_CR8","unstructured":"Wu, C., Wu, F., Qi, T., Huang, Y., Xie, X.: Fastformer: additive attention can be all you need. ArXiv Preprint ArXiv:2108.09084 (2021)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings Of The IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"3_CR10","unstructured":"Shazeer, N., Lan, Z., Cheng, Y., Ding, N., Hou, L.: Talking-heads attention. ArXiv Preprint ArXiv:2003.02436. (2020)"},{"key":"3_CR11","unstructured":"Wu, Z., Liu, Z., Lin, J., Lin, Y., Han, S.: Lite transformer with long-short range attention. In: 8th International Conference On Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26\u201330 April 2020 (2020)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: ChineseBERT: Chinese pretraining enhanced by glyph and pinyin information. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference On Natural Language Processing, vol. 1: Long Papers), pp. 2065\u20132075 (2021)","DOI":"10.18653\/v1\/2021.acl-long.161"},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"3910","DOI":"10.1109\/TPAMI.2024.3355890","volume":"46","author":"H He","year":"2024","unstructured":"He, H., et al.: Pruning self-attentions into convolutional layers in single path. IEEE Trans. Pattern Anal. Mach. Intell. 46, 3910\u20133922 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR14","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26\u201330 April 2020 (2020)"},{"key":"3_CR15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"A Roy","year":"2021","unstructured":"Roy, A., Saffar, M., Vaswani, A., Grangier, D.: Efficient content-based sparse attention with routing transformers. Trans. Assoc. Comput. Linguist. 9, 53\u201368 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"3_CR16","unstructured":"Gerami, A., Hoover, M., Dulepet, P., Duraiswami, R.: FAST: factorizable attention for speeding up transformers. ArXiv Preprint ArXiv:2402.07901 (2024)"},{"key":"3_CR17","unstructured":"Hu, J., et al. Multi-matrix factorization attention. ArXiv Preprint ArXiv:2412.19255 (2024)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Titov, I., Sennrich, R.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: ACL 2019-57th Annual Meeting Of The Association For Computational Linguistics, Proceedings of the Conference, pp. 5797\u20135808 (2020)","DOI":"10.18653\/v1\/P19-1580"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Chatzianastasis, M., Lutzeyer, J., Dasoulas, G., Vazirgiannis, M.: Graph ordering attention networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 7006\u20137014 (2023)","DOI":"10.1609\/aaai.v37i6.25856"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Wang, J., Lin, T., Huang, G.: Graph quaternion-valued attention networks for node classification. In: Proceedings Of The 2023 4th International Conference on Computing, Networks and Internet of Things, pp. 673-677 (2023)","DOI":"10.1145\/3603781.3603900"},{"key":"3_CR21","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.neunet.2020.08.021","volume":"132","author":"Y Xie","year":"2020","unstructured":"Xie, Y., Zhang, Y., Gong, M., Tang, Z., Han, C.: MGAT: multi-view graph attention networks. Neural Netw. 132, 180\u2013189 (2020)","journal-title":"Neural Netw."},{"key":"3_CR22","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1109\/TKDE.2021.3072345","volume":"35","author":"Y Ye","year":"2021","unstructured":"Ye, Y., Ji, S.: Sparse graph attention networks. IEEE Trans. Knowl. Data Eng. 35, 905\u2013916 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."}],"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\/978-981-92-2864-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T06:21:49Z","timestamp":1783837309000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2864-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"ISBN":["9789819228669","9789819228645"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2864-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"13 July 2026","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":"Beijing","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","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":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}