{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:59:27Z","timestamp":1772906367800,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781711","type":"print"},{"value":"9783031781728","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78172-8_1","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:46:44Z","timestamp":1733132804000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["TaylorShift: Shifting the\u00a0Complexity of\u00a0Self-attention from\u00a0Squared to\u00a0Linear (and Back) Using Taylor-Softmax"],"prefix":"10.1007","author":[{"given":"Tobias Christian","family":"Nauen","sequence":"first","affiliation":[]},{"given":"Sebastian","family":"Palacio","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Dengel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"1_CR1","first-page":"12726","volume":"45","author":"F Babiloni","year":"2023","unstructured":"Babiloni, F., et al.: Linear complexity self-attention with 3rd order polynomials. TPAMI 45, 12726\u201312737 (2023)","journal-title":"TPAMI"},{"key":"1_CR2","unstructured":"de\u00a0Br\u00e9bisson, A., Vincent, P.: An exploration of softmax alternatives belonging to the spherical loss family. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2016)"},{"key":"1_CR3","unstructured":"Bulatov, A., Kuratov, Y., Burtsev, M.S.: Scaling transformer to 1m tokens and beyond with RMT (2023)"},{"key":"1_CR4","unstructured":"Choromanski, K.M., et al.: Rethinking attention with performers. In: ICLR (2021)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: ACL, pp. 2978\u20132988. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: ICPR. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"1_CR8","unstructured":"El-Nouby, A., et al.: XCiT: cross-covariance image transformers. In: NeurIPS (2021)"},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3586074","volume":"55","author":"Q Fournier","year":"2023","unstructured":"Fournier, Q., Caron, G.M., Aloise, D.: A practical survey on faster and lighter transformers. ACM Comput. Surv. 55, 1\u201340 (2023)","journal-title":"ACM Comput. Surv."},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Gaikwad, A.S., El-Sharkawy, M.: Pruning convolution neural network (squeezenet) using Taylor expansion-based criterion. In: ISSPIT. IEEE (2018)","DOI":"10.1109\/ISSPIT.2018.8705095"},{"key":"1_CR11","unstructured":"Keles, F.D., Wijewardena, P.M., Hegde, C., Keles, F.D., Wijewardena, P.M., Hegde, C.: On the computational complexity of self-attention. In: ALT (2023)"},{"key":"1_CR12","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. ICLR (2020)"},{"key":"1_CR13","unstructured":"Lin, T., Wang, Y., Liu, X., Qiu, X.: A survey of transformers. AI Open"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR15","unstructured":"Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Lin, D., Matsumoto, Y., Mihalcea, R. (eds.) ACL (2011)"},{"key":"1_CR16","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. In: ICLR (2017)"},{"key":"1_CR17","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.patcog.2016.11.008","volume":"65","author":"G Montavon","year":"2015","unstructured":"Montavon, G., Bach, S., Binder, A., Samek, W., M\u00fcller, K.R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211\u2013222 (2015)","journal-title":"Pattern Recogn."},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Nangia, N., Bowman, S.: ListOps: a diagnostic dataset for latent tree learning. In: Cordeiro, S.R., Oraby, S., Pavalanathan, U., Rim, K. (eds.) NAACL (2018)","DOI":"10.18653\/v1\/N18-4013"},{"key":"1_CR19","unstructured":"Nauen, T.C., Palacio, S., Dengel, A.: Which transformer to favor: a comparative analysis of efficiency in vision transformers (2023)"},{"key":"1_CR20","unstructured":"Nivron, O., Parthipan, R., Wischik, D.: Taylorformer: probabalistic modelling for random processes including time series. In: ICMLW (2023)"},{"key":"1_CR21","unstructured":"Peng, H., Pappas, N., Yogatama, D., Schwartz, R., Smith, N.A., Kong, L.: Random feature attention. In: ICLR (2021)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Zhang, K., Wang, C., Luo, W., Li, H., Jin, Z.: MB-TaylorFormer: multi-branch efficient transformer expanded by Taylor formula for image dehazing. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01176"},{"key":"1_CR23","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"1_CR24","unstructured":"Tay, Y., et al.: Long range arena: a benchmark for efficient transformers. In: ICLR (2021)"},{"key":"1_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) NeurIPS (2017)"},{"key":"1_CR26","unstructured":"Vincent, P., de\u00a0Br\u00e9bisson, A., Bouthillier, X.: Efficient exact gradient update for training deep networks with very large sparse targets. In: NeurIPS (2015)"},{"key":"1_CR27","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity (2020)"},{"key":"1_CR28","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.neucom.2020.04.002","volume":"402","author":"C Xing","year":"2020","unstructured":"Xing, C., Wang, M., Dong, C., Duan, C., Wang, Z.: Using Taylor expansion and convolutional sparse representation for image fusion. Neurocomputing 402, 437\u2013455 (2020)","journal-title":"Neurocomputing"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Nystr\u00f6mformer: a Nystr\u00f6m-based algorithm for approximating self-attention. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"1_CR30","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: NeurIPS (2020)"},{"key":"1_CR31","unstructured":"Zhao, H., et al.: TaylorNet: a Taylor-driven generic neural architecture (2023)"},{"key":"1_CR32","unstructured":"Zheng, L., Yuan, J., Wang, C., Kong, L.: Efficient attention via control variates. In: ICLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78172-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:03:12Z","timestamp":1733133792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78172-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031781711","9783031781728"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78172-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}