{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:42:20Z","timestamp":1778539340468,"version":"3.51.4"},"reference-count":79,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"National Social Science Foundation Major Project of China","award":["20&ZD047"],"award-info":[{"award-number":["20&ZD047"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62037001, 62307032"],"award-info":[{"award-number":["62037001, 62307032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>\n            Knowledge tracing (KT) is a fundamental task in intelligent education aimed at tracking students\u2019 knowledge status and predicting their performance on new questions. The primary challenge in KT is accurately inferring a high-quality representation of students\u2019 knowledge state that effectively captures their understanding of questions. However, existing methods are typically developed under the assumption that students\u2019 behaviors directly reflect their knowledge state, which may not hold true especially in online learning scenarios. Abnormal behaviors exhibited by students, such as guessing and plagiarism, can introduce biases into the data, making it difficult to accurately assess students\u2019 true knowledge state. To address this limitation, we propose a novel DebiAsed Cognition rEpresentation (DACE) modeling approach. This approach introduces a novel adversarial training strategy based on information bottleneck theory to obtain a debiased knowledge state representation that retains only the most reliable information for accurately predicting students\u2019 performance on new questions. Moreover, we design a novel contrastive learning module through embedding-based augmentation to further enhance the robustness and generalizability of the learned knowledge state representation. We conduct extensive experiments on three public KT datasets and the newly released dataset BaiPy to demonstrate the superiority of our model over strong baselines, particularly when confronted with biased data. Our code and datasets are available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/lvXiangwei\/DACE.git\">https:\/\/github.com\/lvXiangwei\/DACE.git<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3736576","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T11:52:32Z","timestamp":1748001152000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Debiased Cognition Representation Learning for Knowledge Tracing"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7682-7317","authenticated-orcid":false,"given":"Xiangwei","family":"Lv","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7021-1047","authenticated-orcid":false,"given":"Guifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0415-6937","authenticated-orcid":false,"given":"Jingyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8705-8138","authenticated-orcid":false,"given":"Hejian","family":"Su","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0367-1138","authenticated-orcid":false,"given":"Zhiang","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1632-9954","authenticated-orcid":false,"given":"Yumeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-217X","authenticated-orcid":false,"given":"Beishui","family":"Liao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3569576"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2784440"},{"key":"e_1_3_2_4_2","first-page":"214","volume-title":"International Conference on Machine Learning","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein generative adversarial networks. In International Conference on Machine Learning. PMLR, 214\u2013223."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69132-7_44"},{"key":"e_1_3_2_6_2","first-page":"531","volume-title":"International Conference on Machine Learning","author":"Belghazi Mohamed Ishmael","year":"2018","unstructured":"Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, and Devon Hjelm. 2018. Mutual information neural estimation. In International Conference on Machine Learning. PMLR, 531\u2013540."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jebo.2020.12.004"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/stats6030046"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564284"},{"key":"e_1_3_2_10_2","first-page":"1597","volume-title":"International Conference on Machine Learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning. PMLR, 1597\u20131607."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28673"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52240-7_13"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01099821"},{"key":"e_1_3_2_14_2","unstructured":"Zhiang Dong Jingyuan Chen and Fei Wu. 2025. Knowledge is power: Harnessing large language models for enhanced cognitive diagnosis. arXiv:2502.05556. Retrieved from https:\/\/arxiv.org\/abs\/2502.05556"},{"key":"e_1_3_2_15_2","volume-title":"ACM Transactions on Information Systems","author":"Dong Zhiang","unstructured":"Zhiang Dong, Liya Hu, Jingyuan Chen, Zhihua Wang, and Fei Wu. 2025. Comprehend then predict: Prompting large language models for recommendation with semantic and collaborative data. ACM Transactions on Information Systems. Just Accepted."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5214\/ans.0972.7531.200408"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10805-014-9207-1"},{"key":"e_1_3_2_18_2","unstructured":"Marco Federici Anjan Dutta Patrick Forr\u00e9 Nate Kushman and Zeynep Akata. 2020. Learning robust representations via multi-view information bottleneck. arXiv:2002.07017. Retrieved from https:\/\/arxiv.org\/abs\/2002.07017"},{"key":"e_1_3_2_19_2","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv:2104.08821. Retrieved from https:\/\/arxiv.org\/abs\/2104.08821"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403282"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1080\/00461520.2014.999919"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589340"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366349"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3418098"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592073"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2460296.2460330"},{"key":"e_1_3_2_28_2","article-title":"New possibilities for the photogrammetry education in Turkey","volume":"34","author":"K\u00fcl\u00fcr S\u0131tk\u0131","year":"1949","unstructured":"S\u0131tk\u0131 K\u00fcl\u00fcr. 1949. New possibilities for the photogrammetry education in Turkey. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 34 (1949), Part 6.","journal-title":"The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512105"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612314"},{"key":"e_1_3_2_31_2","first-page":"14900","article-title":"Anti-backdoor learning: Training clean models on poisoned data","volume":"34","author":"Li Yige","year":"2021","unstructured":"Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, and Xingjun Ma. 2021. Anti-backdoor learning: Training clean models on poisoned data. Advances in Neural Information Processing Systems 34 (2021), 14900\u201314912.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113564"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00373"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3568030"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645582"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2924374"},{"key":"e_1_3_2_37_2","unstructured":"Qi Liu Shuanghong Shen Zhenya Huang Enhong Chen and Yonghe Zheng. 2021. A survey of knowledge tracing. arXiv:2105.15106. Retrieved from https:\/\/arxiv.org\/abs\/2105.15106"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1362-z"},{"key":"e_1_3_2_40_2","unstructured":"Yunfei Liu Yang Yang Xianyu Chen Jian Shen Haifeng Zhang and Yong Yu. 2020. Improving knowledge tracing via pre-training question embeddings. arXiv:2012.05031. Retrieved from https:\/\/arxiv.org\/abs\/2012.05031"},{"key":"e_1_3_2_41_2","unstructured":"Zitao Liu Qiongqiong Liu Jiahao Chen Shuyan Huang and Weiqi Luo. 2023. simpleKT: A simple but tough-to-beat baseline for knowledge tracing. arXiv:2302.06881. Retrieved from https:\/\/arxiv.org\/abs\/2302.06881"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203056615"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1111\/bmsp.12175"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714743"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11948-020-00198-1"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21560"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1111\/jcal.12719"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3350546.3352513"},{"key":"e_1_3_2_49_2","first-page":"21008","article-title":"Perturbation theory for the information bottleneck","volume":"34","author":"Ngampruetikorn Vudtiwat","year":"2021","unstructured":"Vudtiwat Ngampruetikorn and David J. Schwab. 2021. Perturbation theory for the information bottleneck. Advances in Neural Information Processing Systems 34 (2021), 21008\u201321018.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1506855112"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3365103"},{"key":"e_1_3_2_52_2","unstructured":"Shalini Pandey and George Karypis. 2019. A self-attentive model for knowledge tracing. arXiv:1907.06837. Retrieved from https:\/\/arxiv.org\/abs\/2302.06881"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22362-4_21"},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Judea Pearl. 2009. Causal inference in statistics: An overview. Statistics Surveys 3 (2009) 96\u2013146.","DOI":"10.1214\/09-SS057"},{"key":"e_1_3_2_55_2","volume-title":"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. In Advances in Neural Information Processing Systems. C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/bac9162b47c56fc8a4d2a519803d51b3-Paper.pdf"},{"key":"e_1_3_2_56_2","article-title":"Adversarial training for free!","volume":"32","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi, Mahyar Najibi, Mohammad Amin Ghiasi, Zheng Xu, John Dickerson, Christoph Studer, Larry, S. Davis, Gavin Taylor, and Tom Goldstein. 2019. Adversarial training for free!. In Advances in Neural Information Processing Systems, Vol. 32.","journal-title":"Advances in Neural Information Processing Systems, Vol"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"issue":"8","key":"e_1_3_2_58_2","first-page":"8213","article-title":"Monitoring student progress for learning process-consistent knowledge tracing","volume":"35","author":"Shen Shuanghong","year":"2022","unstructured":"Shuanghong Shen, Enhong Chen, Qi Liu, Zhenya Huang, Wei Huang, Yu Yin, Yu Su, and Shijin Wang. 2022. Monitoring student progress for learning process-consistent knowledge tracing. IEEE Transactions on Knowledge and Data Engineering 35, 8 (2022), 8213\u20138227.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108274"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01136"},{"key":"e_1_3_2_61_2","doi-asserted-by":"crossref","unstructured":"Mack Sweeney Huzefa Rangwala Jaime Lester and Aditya Johri. 2016. Next-term student performance prediction: A recommender systems approach. arXiv:1604.01840. Retrieved from https:\/\/arziv.org\/abs\/1604.01840","DOI":"10.1109\/BigData.2015.7363847"},{"key":"e_1_3_2_62_2","volume-title":"International Conference on User Modeling, Adaptation and Personalization","author":"Thai-Nghe Nguyen","year":"2012","unstructured":"Nguyen Thai-Nghe, Lucas Drumond, Tom\u00e1s Horv\u00e1th, and Lars Schmidt-Thieme. 2012. Using factorization machines for student modeling. In International Conference on User Modeling, Adaptation and Personalization."},{"key":"e_1_3_2_63_2","unstructured":"Naftali Tishby Fernando C. Pereira and William Bialek. 2000. The information bottleneck method. arXiv:physics\/0004057. Retrieved from https:\/\/arxiv.org\/abs\/physics\/0004057"},{"key":"e_1_3_2_64_2","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. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems, Vol"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301750"},{"key":"e_1_3_2_66_2","unstructured":"Xin Wang Hong Chen Si\u2019ao Tang Zihao Wu and Wenwu Zhu. 2022. Disentangled representation learning. arXiv:2211.11695. Retrieved from https:\/\/arxiv.org\/abs\/2211.11695"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1111\/emip.12165"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117681"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681632"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599407"},{"key":"e_1_3_2_72_2","first-page":"241","volume-title":"EDM","author":"Xu Yanbo","year":"2011","unstructured":"Yanbo Xu and Jack Mostow. 2011. Using logistic regression to trace multiple sub-skills in a dynamic Bayes net. In EDM. M. Pechenizkiy, T. Calders, C. Conati, S. Ventura, C. Romero, and J. C. Stamper (Eds.), Citeseer, 241\u2013246."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714749"},{"key":"e_1_3_2_74_2","first-page":"299","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","author":"Yang Yang","year":"2020","unstructured":"Yang Yang, Jian Shen, Yanru Qu, Yunfei Liu, Kerong Wang, Yaoming Zhu, Weinan Zhang, and Yong Yu. 2020. GIKT: A graph-based interaction model for knowledge tracing. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 299\u2013315."},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583255"},{"key":"e_1_3_2_76_2","unstructured":"Bo Yuan Yulin Chen Yin Zhang and Wei Jiang. 2025. Hide and seek in noise labels: Noise-robust collaborative active learning with LLM-powered assistance. arXiv:2504.02901. Retrieved from https:\/\/arxiv.org\/abs\/2504.02901"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052580"},{"key":"e_1_3_2_78_2","unstructured":"Yiyun Zhou Wenkang Han and Jingyuan Chen. 2025. Revisiting applicable and comprehensive knowledge tracing in Large-Scale data. arXiv:2501.14256. Retrieved from https:\/\/arxiv.org\/abs\/2501.14256"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714607"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/TLT.2023.3264772"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T10:18:48Z","timestamp":1752661128000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3736576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":79,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3736576"],"URL":"https:\/\/doi.org\/10.1145\/3736576","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]},"assertion":[{"value":"2024-06-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}