{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:36:42Z","timestamp":1783035402140,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759853","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:05:39Z","timestamp":1762963539000},"page":"1085-1098","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9628-3326","authenticated-orcid":false,"given":"Huangliang","family":"Dai","sequence":"first","affiliation":[{"name":"University of California, Riverside, Riverside, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8637-3307","authenticated-orcid":false,"given":"Shixun","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5092-3987","authenticated-orcid":false,"given":"Jiajun","family":"Huang","sequence":"additional","affiliation":[{"name":"University of South Florida, Tampa, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2079-8130","authenticated-orcid":false,"given":"Zizhe","family":"Jian","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2273-5618","authenticated-orcid":false,"given":"Yue","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8299-6124","authenticated-orcid":false,"given":"Haiyang","family":"Hu","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2578-4940","authenticated-orcid":false,"given":"Zizhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"R.C. Baumann. 2005. Radiation-induced soft errors in advanced semiconductor technologies. IEEE Transactions on Device and Materials Reliability 5 3 (2005) 305\u2013316. 10.1109\/TDMR.2005.853449","DOI":"10.1109\/TDMR.2005.853449"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Shekhar Borkar. 2005. Designing reliable systems from unreliable components: the challenges of transistor variability and degradation. Ieee Micro 25 6 (2005) 10\u201316.","DOI":"10.1109\/MM.2005.110"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Cristiano Castelfranchi. 1998. Modelling social action for AI agents. Artificial intelligence 103 1-2 (1998) 157\u2013182.","DOI":"10.1016\/S0004-3702(98)00056-3"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1994.315624"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298655"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137773"},{"key":"e_1_3_3_2_8_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Dao Tri","year":"2024","unstructured":"Tri Dao. 2024. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=mZn2Xyh9Ec"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Tri Dao Dan Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35 (2022) 16344\u201316359.","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_2_10_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-92137-0_28"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448891.3448936"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"M.D. Emmerson and R.I. Damper. 1993. Determining and improving the fault tolerance of multilayer perceptrons in a pattern-recognition application. IEEE Transactions on Neural Networks 4 5 (1993) 788\u2013793. 10.1109\/72.248456","DOI":"10.1109\/72.248456"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45255-9_47"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"David Freitas C\u00e9sar Marcon Jarbas Silveira Lirida Naviner and Jo\u00e3o Mota. 2022. A survey on two-dimensional Error Correction Codes applied to fault-tolerant systems. Microelectronics Reliability 139 (2022) 114826.","DOI":"10.1016\/j.microrel.2022.114826"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/DFT.2019.8875314"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Zhen Gao Ziye Yin Jingyan Wang Rui Su Jie Deng Qiang Liu Pedro Reviriego Shanshan Liu and Fabrizio Lombardi. 2025. On the Dependability of Bidirectional Encoder Representations from Transformers (BERT) to Soft Errors. IEEE Transactions on Nanotechnology 24 (2025) 73\u201387. 10.1109\/TNANO.2025.3531721","DOI":"10.1109\/TNANO.2025.3531721"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774635"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.15439\/2020F20"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2019.8702382"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et\u00a0al. 2022. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence 45 1 (2022) 87\u2013110.","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Kuang-Hua Huang and Jacob\u00a0A. Abraham. 1984. Algorithm-Based Fault Tolerance for Matrix Operations. IEEE Trans. Comput. C-33 6 (1984) 518\u2013528. 10.1109\/TC.1984.1676475","DOI":"10.1109\/TC.1984.1676475"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Younis Ibrahim Haibin Wang Junyang Liu Jinghe Wei Li Chen Paolo Rech Khalid Adam and Gang Guo. 2020. Soft errors in DNN accelerators: A comprehensive review. Microelectronics Reliability 115 (2020) 113969.","DOI":"10.1016\/j.microrel.2020.113969"},{"key":"e_1_3_3_2_24_2","first-page":"5156","volume-title":"International conference on machine learning","author":"Katharopoulos Angelos","year":"2020","unstructured":"Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Fran\u00e7ois Fleuret. 2020. Transformers are rnns: Fast autoregressive transformers with linear attention. In International conference on machine learning. PMLR, 5156\u20135165."},{"key":"e_1_3_3_2_25_2","volume-title":"International Conference on Learning Representations","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, Lukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The Efficient Transformer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkgNKkHtvB"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476184"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Hongliang Li Hairui Zhao Ting Sun Xiang Li Haixiao Xu and Keqin Li. 2024. Interference-aware opportunistic job placement for shared distributed deep learning clusters. J. Parallel and Distrib. Comput. 183 (2024) 104776.","DOI":"10.1016\/j.jpdc.2023.104776"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710870"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317742"},{"key":"e_1_3_3_2_30_2","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.11692 364 (2019)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Amir\u00a0Moosavie Nia and Karim Mohammadi. 2007. A generalized ABFT technique using a fault tolerant neural network. Journal of Circuits Systems and Computers 16 03 (2007) 337\u2013356.","DOI":"10.1142\/S0218126607003708"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446091"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"E.\u00a0L. Petersen R. Koga M.\u00a0A. Shoga J.\u00a0C. Pickel and W.\u00a0E. Price. 2013. The Single Event Revolution. IEEE Transactions on Nuclear Science 60 3 (2013) 1824\u20131835. 10.1109\/TNS.2013.2248065","DOI":"10.1109\/TNS.2013.2248065"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"D.S. Phatak and I. Koren. 1995. Complete and partial fault tolerance of feedforward neural nets. IEEE Transactions on Neural Networks 6 2 (1995) 446\u2013456. 10.1109\/72.363479","DOI":"10.1109\/72.363479"},{"key":"e_1_3_3_2_35_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465834"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.34"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Aurko Roy Mohammad Saffar Ashish Vaswani and David Grangier. 2021. Efficient content-based sparse attention with routing transformers. Transactions of the Association for Computational Linguistics 9 (2021) 53\u201368.","DOI":"10.1162\/tacl_a_00353"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"J. Sosnowski. 1989. Fault Tolerant DMR Miroprocessor System. IFAC Proceedings Volumes 22 19 (1989) 141\u2013146. 10.1016\/S1474-6670(17)52809-8IFAC\/IFIP Workshop on Safety of Computer Control Systems 1989 (SAFECOMP \u201989) Vienna Austria 5-7 December.","DOI":"10.1016\/S1474-6670(17)52809-8"},{"key":"e_1_3_3_2_40_2","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew\u00a0M Dai Anja Hauth Katie Millican et\u00a0al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11805 (2023)."},{"key":"e_1_3_3_2_41_2","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_3_2_42_2","unstructured":"Sinong Wang Belinda\u00a0Z Li Madian Khabsa Han Fang and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.04768 (2020)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER59578.2024.00035"},{"key":"e_1_3_3_2_45_2","unstructured":"Shixun Wu Yujia Zhai Jinyang Liu Jiajun Huang Zizhe Jian Huangliang Dai Sheng Di Zizhong Chen and Franck Cappello. 2024. Turbofft: A high-performance fast fourier transform with fault tolerance on gpu. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.02520 (2024)."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Peng Xu Xiatian Zhu and David\u00a0A Clifton. 2023. Multimodal learning with transformers: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 10 (2023) 12113\u201312132.","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Xinghua Xue Cheng Liu Ying Wang Bing Yang Tao Luo Lei Zhang Huawei Li and Xiaowei Li. 2023. Soft Error Reliability Analysis of Vision Transformers. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 31 12 (2023) 2126\u20132136. 10.1109\/TVLSI.2023.3317138","DOI":"10.1109\/TVLSI.2023.3317138"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","unstructured":"Jinyu Zhan Ruoxu Sun Wei Jiang Yucheng Jiang Xunzhao Yin and Cheng Zhuo. 2022. Improving Fault Tolerance for Reliable DNN Using Boundary-Aware Activation. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 10 (2022) 3414\u20133425. 10.1109\/TCAD.2021.3129114","DOI":"10.1109\/TCAD.2021.3129114"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044666"},{"key":"e_1_3_3_2_50_2","first-page":"143","volume-title":"2025 USENIX Annual Technical Conference (USENIX ATC 25)","author":"Zhao Hairui","year":"2025","unstructured":"Hairui Zhao, Qi Tian, Hongliang Li, and Zizhong Chen. 2025. { FlexPipe} : Maximizing Training Efficiency for Transformer-based Models with { Variable-Length} Inputs. In 2025 USENIX Annual Technical Conference (USENIX ATC 25). 143\u2013159."},{"key":"e_1_3_3_2_51_2","unstructured":"Kai Zhao Sheng Di Sihuan Li Xin Liang Yujia Zhai Jieyang Chen Kaiming Ouyang Franck Cappello and Zizhong Chen. 2020. FT-CNN: Algorithm-based fault tolerance for convolutional neural networks. IEEE Transactions on Parallel and Distributed Systems 32 7 (2020) 1677\u20131689."}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:32:00Z","timestamp":1773253920000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":50,"alternative-id":["10.1145\/3712285.3759853","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759853","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}