{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T14:45:03Z","timestamp":1767192303531,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2033"],"award-info":[{"award-number":["U22A2033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY22F020023","LZ22F020015","61972122"],"award-info":[{"award-number":["LY22F020023","LZ22F020015","61972122"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s12650-024-00985-z","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T14:01:45Z","timestamp":1712930505000},"page":"731-748","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["BHPVAS: visual analysis system for pruning attention heads in BERT model"],"prefix":"10.1007","volume":"27","author":[{"given":"Zhen","family":"Liu","sequence":"first","affiliation":[]},{"given":"Haibo","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Huawei","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Xinyu","family":"Hong","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2599-506X","authenticated-orcid":false,"given":"Xiangyang","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"issue":"1","key":"985_CR1","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TVCG.2019.2934262","volume":"26","author":"Y Ahn","year":"2020","unstructured":"Ahn Y, Lin Y-R (2020) Fairsight: visual analytics for fairness in decision making. IEEE Trans Vis Comput Graph 26(1):1086\u20131095. https:\/\/doi.org\/10.1109\/TVCG.2019.2934262","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR2","doi-asserted-by":"publisher","unstructured":"Aken B, Winter B, L\u00f6ser A, Gers FA (2020) Visbert: hidden-state visualizations for transformers. In: Companion proceedings of the web conference 2020, WWW\u201920. Association for Computing Machinery, New York, pp 207\u2013211. https:\/\/doi.org\/10.1145\/3366424.3383542","DOI":"10.1145\/3366424.3383542"},{"key":"985_CR3","doi-asserted-by":"publisher","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Proceedings of the 34th international conference on neural information processing systems, NIPS\u201920. Curran Associates Inc., Red Hook. https:\/\/doi.org\/10.5555\/3495724.3495883","DOI":"10.5555\/3495724.3495883"},{"issue":"7","key":"985_CR4","doi-asserted-by":"publisher","first-page":"3289","DOI":"10.1109\/TVCG.2020.2969185","volume":"27","author":"K Cao","year":"2021","unstructured":"Cao K, Liu M, Su H, Wu J, Zhu J, Liu S (2021) Analyzing the noise robustness of deep neural networks. IEEE Trans Vis Comput Graph 27(7):3289\u20133304. https:\/\/doi.org\/10.1109\/TVCG.2020.2969185","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR5","doi-asserted-by":"publisher","unstructured":"Carreira-Perpinan MA, Idelbayev Y (2018) Learning-compression\u201d algorithms for neural net pruning. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 8532\u20138541. https:\/\/doi.org\/10.1109\/CVPR.2018.00890","DOI":"10.1109\/CVPR.2018.00890"},{"issue":"1","key":"985_CR6","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1109\/TVCG.2018.2864477","volume":"25","author":"M Cavallo","year":"2018","unstructured":"Cavallo M, Demiralp \u00c7 (2018) Clustrophile 2: guided visual clustering analysis. IEEE Trans Vis Comput Graph 25(1):267\u2013276. https:\/\/doi.org\/10.1109\/TVCG.2018.2864477","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR7","doi-asserted-by":"publisher","unstructured":"Chauvin Y (1988) A back-propagation algorithm with optimal use of hidden units. In: Proceedings of the 1st international conference on neural information processing systems, NIPS\u201988. MIT Press, Cambridge, pp 519\u2013526. https:\/\/doi.org\/10.5555\/2969735.2969795","DOI":"10.5555\/2969735.2969795"},{"key":"985_CR8","doi-asserted-by":"publisher","unstructured":"Chiliang Z, Tao H, Yingda G, Zuochang Y (2019) Accelerating convolutional neural networks with dynamic channel pruning. In: 2019 Data compression conference (DCC), pp 563\u2013563. https:\/\/doi.org\/10.1109\/DCC.2019.00075","DOI":"10.1109\/DCC.2019.00075"},{"issue":"1","key":"985_CR9","doi-asserted-by":"publisher","first-page":"795","DOI":"10.5555\/2503308.2188413","volume":"13","author":"C Cortes","year":"2012","unstructured":"Cortes C, Mohri M, Rostamizadeh A (2012) Algorithms for learning kernels based on centered alignment. J Mach Learn Res 13(1):795\u2013828. https:\/\/doi.org\/10.5555\/2503308.2188413","journal-title":"J Mach Learn Res"},{"issue":"2","key":"985_CR10","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TVCG.2020.3028976","volume":"27","author":"JF DeRose","year":"2021","unstructured":"DeRose JF, Wang J, Berger M (2021) Attention flows: Analyzing and comparing attention mechanisms in language models. IEEE Trans Vis Comput Graph 27(2):1160\u20131170. https:\/\/doi.org\/10.1109\/TVCG.2020.3028976","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR11","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019). 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, volume 1 (long and short papers). Association for Computational Linguistics, Minneapolis, pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"985_CR12","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/978-3-031-10602-6_17","volume-title":"Uniform manifold approximation and projection (UMAP)","author":"B Ghojogh","year":"2023","unstructured":"Ghojogh B, Crowley M, Karray F, Ghodsi A (2023) Uniform manifold approximation and projection (UMAP). Springer, Cham, pp 479\u2013497. https:\/\/doi.org\/10.1007\/978-3-031-10602-6_17"},{"key":"985_CR13","doi-asserted-by":"publisher","unstructured":"Gordon M, Duh K, Andrews N (2020) Compressing BERT: studying the effects of weight pruning on transfer learning. In: Proceedings of the 5th workshop on representation learning for NLP. Association for Computational Linguistics, Online, pp 143\u2013155. https:\/\/doi.org\/10.18653\/v1\/2020.repl4nlp-1.18","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"985_CR14","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/11564089_7","volume-title":"Algorithmic learning theory","author":"A Gretton","year":"2005","unstructured":"Gretton A, Bousquet O, Smola A, Sch\u00f6lkopf B (2005) Measuring statistical dependence with Hilbert\u2013Schmidt norms. In: Jain S, Simon HU, Tomita E (eds) Algorithmic learning theory. Springer, Berlin, pp 63\u201377. https:\/\/doi.org\/10.1007\/11564089_7"},{"key":"985_CR15","unstructured":"Guo F-M, Liu S, Mungall FS, Lin X, Wang Y (2019) Reweighted proximal pruning for large-scale language representation. ArXiv arXiv:1909.12486"},{"key":"985_CR16","unstructured":"Guo F-M, Liu S, Mungall FS, Lin X, Wang Y (2020) Reweighted proximal pruning for large-scale language representation"},{"key":"985_CR17","doi-asserted-by":"publisher","unstructured":"Guo Y, Yao A, Chen Y (2016) Dynamic network surgery for efficient DNNs. In: Proceedings of the 30th international conference on neural information processing systems, NIPS\u201916. Curran Associates Inc., Red Hook, pp 1387\u20131395. https:\/\/doi.org\/10.5555\/3157096.3157251","DOI":"10.5555\/3157096.3157251"},{"key":"985_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0013-1","author":"D Han","year":"2022","unstructured":"Han D, Pan J, Pan R, Zhou D, Cao N, He J, Xu M, Chen W (2022) inet: Visual analysis of irregular transition in multivariate dynamic networks. Front Comput Sci. https:\/\/doi.org\/10.1007\/s11704-020-0013-1","journal-title":"Front Comput Sci"},{"key":"985_CR19","doi-asserted-by":"publisher","DOI":"10.3390\/s19163607","author":"M Han","year":"2019","unstructured":"Han M, Kim J (2019) Joint banknote recognition and counterfeit detection using explainable artificial intelligence. Sensors. https:\/\/doi.org\/10.3390\/s19163607","journal-title":"Sensors"},{"key":"985_CR20","doi-asserted-by":"publisher","unstructured":"Han S, Pool J, Tran J, Dally WJ (2015) Learning both weights and connections for efficient neural networks. In: Proceedings of the 28th international conference on neural information processing systems\u2014volume 1, NIPS\u201915. MIT Press, Cambridge, pp 1135\u20131143. https:\/\/doi.org\/10.5555\/2969239.2969366","DOI":"10.5555\/2969239.2969366"},{"key":"985_CR21","doi-asserted-by":"publisher","unstructured":"He T, Jin X, Ding G, Yi L, Yan C (2019) Towards better uncertainty sampling: active learning with multiple views for deep convolutional neural network. In: 2019 IEEE international conference on multimedia and expo (ICME), pp 1360\u20131365. https:\/\/doi.org\/10.1109\/ICME.2019.00236","DOI":"10.1109\/ICME.2019.00236"},{"key":"985_CR22","doi-asserted-by":"publisher","unstructured":"He Y, Zhang X, Sun J (2017) Channel pruning for accelerating very deep neural networks. In: 2017 IEEE international conference on computer vision (ICCV), pp 1398\u20131406. https:\/\/doi.org\/10.1109\/ICCV.2017.155","DOI":"10.1109\/ICCV.2017.155"},{"issue":"2","key":"985_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.visinf.2021.03.003","volume":"5","author":"X Ji","year":"2021","unstructured":"Ji X, Tu Y, He W, Wang J, Shen H-W, Yen P-Y (2021) Usevis: visual analytics of attention-based neural embedding in information retrieval. Vis Inform 5(2):1\u201312. https:\/\/doi.org\/10.1016\/j.visinf.2021.03.003","journal-title":"Vis Inform"},{"issue":"1","key":"985_CR24","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/TVCG.2017.2744718","volume":"24","author":"M Kahng","year":"2018","unstructured":"Kahng M, Andrews PY, Kalro A, Chau DH (2018) Activis: visual exploration of industry-scale deep neural network models. IEEE Trans Vis Comput Graph 24(1):88\u201397. https:\/\/doi.org\/10.1109\/TVCG.2017.2744718","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR25","unstructured":"Kornblith S, Norouzi M, Lee H, Hinton G (2019). Similarity of neural network representations revisited. In: International conference on machine learning. PMLR, pp 3519\u20133529"},{"key":"985_CR26","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1007\/s10115-017-1029-1","volume":"52","author":"S Leroux","year":"2017","unstructured":"Leroux S, Bohez S, De Coninck E, Verbelen T, Vankeirsbilck B, Simoens P, Dhoedt B (2017) The cascading neural network: building the internet of smart things. Knowl Inf Syst 52:791\u2013814. https:\/\/doi.org\/10.1007\/s10115-017-1029-1","journal-title":"Knowl Inf Syst"},{"key":"985_CR27","unstructured":"Lin J, Rao Y, Lu J, Zhou J (2017a) Runtime neural pruning. In: NIPS, pp 2178\u20132188"},{"key":"985_CR28","doi-asserted-by":"publisher","unstructured":"Luo J-H, Wu J, Lin W (2017b) Thinet: a filter level pruning method for deep neural network compression. In: 2017 IEEE International conference on computer vision (ICCV), pp 5068\u20135076. https:\/\/doi.org\/10.1109\/ICCV.2017.541","DOI":"10.1109\/ICCV.2017.541"},{"key":"985_CR29","unstructured":"MarietZ Sara S (2016) Diversity networks: neural network compression using determinantal point processes. In: Proceedings of the 4th international conference on learning representations, pp 67\u201379"},{"key":"985_CR30","doi-asserted-by":"publisher","unstructured":"Michel P, Levy O, Neubig G (2019a) Are sixteen heads really better than one? Curran Associates Inc., Red Hook. https:\/\/doi.org\/10.5555\/3454287.3455544","DOI":"10.5555\/3454287.3455544"},{"key":"985_CR31","unstructured":"Michel P, Levy O, Neubig G (2019b) Are sixteen heads really better than one? In: Neural information processing systems"},{"key":"985_CR32","doi-asserted-by":"publisher","unstructured":"Ming Y, Cao S, Zhang R, Li Z, Chen Y, Song Y, Qu H (2017) Understanding hidden memories of recurrent neural networks. In: 2017 IEEE conference on visual analytics science and technology (VAST), pp 13\u201324. https:\/\/doi.org\/10.1109\/VAST.2017.8585721","DOI":"10.1109\/VAST.2017.8585721"},{"issue":"1","key":"985_CR33","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1109\/TVCG.2019.2934267","volume":"26","author":"Y Ming","year":"2020","unstructured":"Ming Y, Xu P, Cheng F, Qu H, Ren L (2020) Protosteer: steering deep sequence model with prototypes. IEEE Trans Vis Comput Graph 26(1):238\u2013248. https:\/\/doi.org\/10.1109\/TVCG.2019.2934267","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR34","doi-asserted-by":"publisher","unstructured":"Ming Y, Xu P, Qu H, Ren L (2019) Interpretable and steerable sequence learning via prototypes. In: KDD\u201919. Association for Computing Machinery, New York, pp 903\u2013913. https:\/\/doi.org\/10.1145\/3292500.3330908","DOI":"10.1145\/3292500.3330908"},{"key":"985_CR35","doi-asserted-by":"publisher","unstructured":"Mozer M C, Smolensky P (1988) Skeletonization: a technique for trimming the fat from a network via relevance assessment. In: Proceedings of the 1st international conference on neural information processing systems, NIPS\u201988. MIT Press, Cambridge, pp 107\u2013115. https:\/\/doi.org\/10.5555\/2969735.2969748","DOI":"10.5555\/2969735.2969748"},{"key":"985_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-0609-0","author":"Y Peng","year":"2023","unstructured":"Peng Y, Fan X, Chen R, Yu Z, Liu S, Chen Y, Zhao Y, Zhou F (2023) Visual abstraction of dynamic network via improved multi-class blue noise sampling. Front Comput Sci. https:\/\/doi.org\/10.1007\/s11704-021-0609-0","journal-title":"Front Comput Sci"},{"issue":"1","key":"985_CR37","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1109\/TVCG.2017.2744158","volume":"24","author":"H Strobelt","year":"2018","unstructured":"Strobelt H, Gehrmann S, Pfister H, Rush AM (2018) Lstmvis: A tool for visual analysis of hidden state dynamics in recurrent neural networks. IEEE Trans Vis Comput Graph 24(1):667\u2013676. https:\/\/doi.org\/10.1109\/TVCG.2017.2744158","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR38","doi-asserted-by":"publisher","unstructured":"Tan S, Caruana R, Hooker G, Lou Y (2018) Distill-and-compare: auditing black-box models using transparent model distillation. In: Proceedings of the 2018 AAAI\/ACM conference on AI, ethics, and society, AIES\u201918. Association for Computing Machinery, New York, pp 303\u2013310. https:\/\/doi.org\/10.1145\/3278721.3278725","DOI":"10.1145\/3278721.3278725"},{"key":"985_CR39","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems, NIPS\u201917. Curran Associates Inc., Red Hook, pp 6000\u20136010. https:\/\/doi.org\/10.5555\/3295222.3295349","DOI":"10.5555\/3295222.3295349"},{"key":"985_CR40","doi-asserted-by":"publisher","unstructured":"Voita E, Talbot D, Moiseev F, Sennrich R, Titov I (2019) Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: Proceedings of the 57th annual meeting of the association for computational linguistics. Association for Computational Linguistics, Florence, pp 5797\u20135808. https:\/\/doi.org\/10.18653\/v1\/P19-1580","DOI":"10.18653\/v1\/P19-1580"},{"issue":"1","key":"985_CR41","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TVCG.2018.2864504","volume":"25","author":"J Wang","year":"2019","unstructured":"Wang J, Gou L, Shen H-W, Yang H (2019) Dqnviz: a visual analytics approach to understand deep q-networks. IEEE Trans Vis Comput Graph 25(1):288\u2013298. https:\/\/doi.org\/10.1109\/TVCG.2018.2864504","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR42","doi-asserted-by":"publisher","unstructured":"Wang Y, Feng C, Guo C, Chu Y, Hwang J-N (2019) Solving the sparsity problem in recommendations via cross-domain item embedding based on co-clustering. In: Proceedings of the twelfth ACM international conference on web search and data mining, WSDM\u201919. Association for Computing Machinery, New York, pp 717\u2013725. https:\/\/doi.org\/10.1145\/3289600.3290973","DOI":"10.1145\/3289600.3290973"},{"key":"985_CR43","doi-asserted-by":"publisher","unstructured":"Wu Z, Nagarajan T, Kumar A, Rennie S, Davis LS, Grauman K, Feris R (2018) Blockdrop: dynamic inference paths in residual networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 8817\u20138826. https:\/\/doi.org\/10.1109\/CVPR.2018.00919","DOI":"10.1109\/CVPR.2018.00919"},{"key":"985_CR44","doi-asserted-by":"publisher","unstructured":"Xia M, Zhong Z, Chen D (2022) Structured pruning learns compact and accurate models. In: Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Dublin, pp 1513\u20131528. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.107","DOI":"10.18653\/v1\/2022.acl-long.107"},{"issue":"10","key":"985_CR45","doi-asserted-by":"publisher","first-page":"3953","DOI":"10.1109\/TVCG.2020.2995100","volume":"27","author":"W Yang","year":"2021","unstructured":"Yang W, Wang X, Lu J, Dou W, Liu S (2021) Interactive steering of hierarchical clustering. IEEE Trans Vis Comput Graph 27(10):3953\u20133967. https:\/\/doi.org\/10.1109\/TVCG.2020.2995100","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"985_CR46","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/41095-020-0191-7","volume":"7","author":"J Yuan","year":"2021","unstructured":"Yuan J, Chen C, Yang W, Liu M, Xia J, Liu S (2021) A survey of visual analytics techniques for machine learning. Comput Vis Media 7:3\u201336. https:\/\/doi.org\/10.1007\/41095-020-0191-7","journal-title":"Comput Vis Media"}],"container-title":["Journal of Visualization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12650-024-00985-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12650-024-00985-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12650-024-00985-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T14:23:52Z","timestamp":1719843832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12650-024-00985-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["985"],"URL":"https:\/\/doi.org\/10.1007\/s12650-024-00985-z","relation":{},"ISSN":["1343-8875","1875-8975"],"issn-type":[{"type":"print","value":"1343-8875"},{"type":"electronic","value":"1875-8975"}],"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}