{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T22:22:30Z","timestamp":1783549350449,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62477025"],"award-info":[{"award-number":["62477025"]}]},{"name":"Key Laboratory of Smart Education of Guangdong Higher Education Institutes, Jinan University","award":["2022LSYS003"],"award-info":[{"award-number":["2022LSYS003"]}]},{"name":"Beijing Natural Science Foundation","award":["L252010"],"award-info":[{"award-number":["L252010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792272","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"7080-7090","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Frequency-Aware Mixture of Heterogeneous Experts Framework for Knowledge Tracing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1261-7708","authenticated-orcid":false,"given":"Youheng","family":"Bai","sequence":"first","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5225-2195","authenticated-orcid":false,"given":"Mingliang","family":"Hou","sequence":"additional","affiliation":[{"name":"TAL Education Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6604-475X","authenticated-orcid":false,"given":"Teng","family":"Guo","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0491-307X","authenticated-orcid":false,"given":"Zitao","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5605-7397","authenticated-orcid":false,"given":"Weiqi","family":"Luo","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331195"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125988"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.34998"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3733593"},{"key":"e_1_3_2_1_5_1","volume-title":"Digital image processing: principles and applications","author":"Baxes Gregory A","unstructured":"Gregory A Baxes. 1994. Digital image processing: principles and applications. John Wiley & Sons, Inc."},{"key":"e_1_3_2_1_6_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_7_1","volume-title":"The fast Fourier transform and its applications","author":"Brigham E Oran","unstructured":"E Oran Brigham. 1988. The fast Fourier transform and its applications. Prentice-Hall, Inc."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2010.06.031"},{"key":"e_1_3_2_1_9_1","volume-title":"Diversity creation methods: a survey and categorisation. Information fusion 6, 1","author":"Brown Gavin","year":"2005","unstructured":"Gavin Brown, Jeremy Wyatt, Rachel Harris, and Xin Yao. 2005. Diversity creation methods: a survey and categorisation. Information fusion 6, 1 (2005), 5-20."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386527.3405945"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2006.04.004"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.489"},{"key":"e_1_3_2_1_13_1","volume-title":"Learning factored representations in a deep mixture of experts. arXiv preprint arXiv:1312.4314","author":"Eigen David","year":"2013","unstructured":"David Eigen, Marc'Aurelio Ranzato, and Ilya Sutskever. 2013. Learning factored representations in a deep mixture of experts. arXiv preprint arXiv:1312.4314 (2013)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3322706.3361996"},{"key":"e_1_3_2_1_15_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23, 120 (2022), 1-39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403282"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/15598608.2010.10412020"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/99.388960"},{"key":"e_1_3_2_1_19_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475554"},{"key":"e_1_3_2_1_21_1","volume-title":"Chi Chao Tung, and Henry H Liu","author":"Huang Norden E","year":"1998","unstructured":"Norden E Huang, Zheng Shen, Steven R Long, Manli C Wu, Hsing H Shih, Quanan Zheng, Nai-Chyuan Yen, Chi Chao Tung, and Henry H Liu. 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences 454, 1971 (1998), 903-995."},{"key":"e_1_3_2_1_22_1","volume-title":"Adaptive mixtures of local experts. Neural computation 3, 1","author":"Jacobs Robert A","year":"1991","unstructured":"Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. 1991. Adaptive mixtures of local experts. Neural computation 3, 1 (1991), 79-87."},{"key":"e_1_3_2_1_23_1","first-page":"190","article-title":"A contextualized, differential sequence mining method to derive students' learning behavior patterns","volume":"5","author":"Kinnebrew John S","year":"2013","unstructured":"John S Kinnebrew, Kirk M Loretz, and Gautam Biswas. 2013. A contextualized, differential sequence mining method to derive students' learning behavior patterns. Journal of Educational Data Mining 5, 1 (2013), 190-219.","journal-title":"Journal of Educational Data Mining"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3303772.3303786"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations.","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling giant Models with conditional computation and automatic sharding. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","volume-title":"A survey of knowledge tracing. arXiv preprint arXiv:2105.15106","author":"Liu Qi","year":"2021","unstructured":"Qi Liu, Shuanghong Shen, Zhenya Huang, Enhong Chen, and Yonghe Zheng. 2021. A survey of knowledge tracing. arXiv preprint arXiv:2105.15106 (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583866"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 11th International Conference on Learning Representations.","author":"Liu Zitao","year":"2022","unstructured":"Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang, and Weiqi Luo. 2022. simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1347"},{"key":"e_1_3_2_1_30_1","volume-title":"XES3G5M: A knowledge tracing benchmark dataset with auxiliary information. Advances in Neural Information Processing Systems 36","author":"Liu Zitao","year":"2024","unstructured":"Zitao Liu, Qiongqiong Liu, Teng Guo, Jiahao Chen, Shuyan Huang, Xiangyu Zhao, Jiliang Tang, Weiqi Luo, and Jian Weng. 2024. XES3G5M: A knowledge tracing benchmark dataset with auxiliary information. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645718"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313565"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3350546.3352513"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 12th International Conference on Educational Data Mining. 384-389","author":"Pandey Shalini","year":"2019","unstructured":"Shalini Pandey and George Karypis. 2019. A self-attentive model for knowledge tracing. In Proceedings of the 12th International Conference on Educational Data Mining. 384-389."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411994"},{"key":"e_1_3_2_1_36_1","volume-title":"Deep Knowledge Tracing. Advances in Neural Information Processing Systems","author":"Piech Chris","year":"2015","unstructured":"Chris Piech, Jonathan Bassen, Jonathan Huang, Surya Ganguli, Mehran Sahami, Leonidas J. Guibas, and Jascha Sohl-Dickstein. 2015. Deep Knowledge Tracing. Advances in Neural Information Processing Systems (2015), 505-513."},{"key":"e_1_3_2_1_37_1","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme Carlos","year":"2021","unstructured":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, Andr\u00e9 Susano Pinto, Daniel Keysers, and Neil Houlsby. 2021. Scaling vision with sparse mixture of experts. Advances in Neural Information Processing Systems 34 (2021), 8583-8595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531939"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467237"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18608\/jla.2016.32.16"},{"key":"e_1_3_2_1_42_1","volume-title":"Hydra: Preserving ensemble diversity for model distillation. arXiv preprint arXiv:2001.04694","author":"Tran Linh","year":"2020","unstructured":"Linh Tran, Bastiaan S Veeling, Kevin Roth, Jakub Swiatkowski, Joshua V Dillon, Jasper Snoek, Stephan Mandt, Tim Salimans, Sebastian Nowozin, and Rodolphe Jenatton. 2020. Hydra: Preserving ensemble diversity for model distillation. arXiv preprint arXiv:2001.04694 (2020)."},{"key":"e_1_3_2_1_43_1","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017), 6000-6010.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441802"},{"key":"e_1_3_2_1_45_1","volume-title":"Richard E Turner, Richard G Baraniuk, Craig Barton, Simon Peyton Jones, et al.","author":"Wang Zichao","year":"2020","unstructured":"Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, Jos\u00e9 Miguel Hern\u00e1ndez-Lobato, Richard E Turner, Richard G Baraniuk, Craig Barton, Simon Peyton Jones, et al. 2020. Instructions and guide for diagnostic questions: The neurips 2020 education challenge. arXiv preprint arXiv:2007.12061 (2020)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3076021"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"e_1_3_2_1_48_1","volume-title":"Deep-IRT: Make deep learning based knowledge tracing explainable using item response theory. arXiv e-prints","author":"Yeung Chun-Kit","year":"2019","unstructured":"Chun-Kit Yeung. 2019. Deep-IRT: Make deep learning based knowledge tracing explainable using item response theory. arXiv e-prints (2019), arXiv\u20131904."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3231644.3231647"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583255"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39112-5_18"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052580"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 2nd International Conference on Signal Processing, Computer Networks and Communications. 245-248","author":"Zhou Bo","year":"2024","unstructured":"Bo Zhou, Yang Song, and Jie Ai. 2024. Time-frequency analysis of non-stationary signals based on short-time Fourier transform. In Proceedings of the 2nd International Conference on Signal Processing, Computer Networks and Communications. 245-248."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:57:50Z","timestamp":1783151870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":54,"alternative-id":["10.1145\/3774904.3792272","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792272","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}