Consistency and Monotonicity Regularization for Neural Knowledge Tracing

Consistency and Monotonicity Regularization for Neural Knowledge Tracing

Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education. In this paper, we present a simple, yet effective strategy to improve the generalization ability of KT models: we propose three types of novel data augmentation, coin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Seewoo, Choi, Youngduck, Park, Juneyoung, Kim, Byungsoo, Shin, Jinwoo
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Lee, Seewoo
Choi, Youngduck
Park, Juneyoung
Kim, Byungsoo
Shin, Jinwoo
description Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education. In this paper, we present a simple, yet effective strategy to improve the generalization ability of KT models: we propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses that impose certain consistency or monotonicity biases on the model's predictions for the original and augmented sequence. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances, under 3 widely-used neural networks and 4 public benchmarks, e.g., it yields 6.3% improvement in AUC under the DKT model and the ASSISTmentsChall dataset.
doi_str_mv 10.48550/arxiv.2105.00607
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2105_00607</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2105_00607</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-cc9974825a1a58f0efce709adab5102b6605f25f35b838ab6804bcf5876a94fc3</originalsourceid><addsrcrecordid>eNotz71OwzAUQGEvDKjwAEz4BRJufq7tjFUEFNGChLJH144dWUpt5KRAeHpEYTrbkT7GbgrIa4UId5S-_EdeFoA5gAB5yXZtDLOfFxvMyikM_BBDXGLwxi8rf7PjaaLkv2nxMXAXE3-xp0QTfw7xc7LDaHmXyPgwXrELR9Nsr_-7Yd3Dfdfusv3r41O73WckpMyMaRpZqxKpIFQOrDNWQkMDaSyg1EIAuhJdhVpVirRQUGvjUElBTe1MtWG3f9szpX9P_khp7X9J_ZlU_QA1NkeQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Consistency and Monotonicity Regularization for Neural Knowledge Tracing</title><source>arXiv.org</source><creator>Lee, Seewoo ; Choi, Youngduck ; Park, Juneyoung ; Kim, Byungsoo ; Shin, Jinwoo</creator><creatorcontrib>Lee, Seewoo ; Choi, Youngduck ; Park, Juneyoung ; Kim, Byungsoo ; Shin, Jinwoo</creatorcontrib><description>Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education. In this paper, we present a simple, yet effective strategy to improve the generalization ability of KT models: we propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses that impose certain consistency or monotonicity biases on the model's predictions for the original and augmented sequence. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances, under 3 widely-used neural networks and 4 public benchmarks, e.g., it yields 6.3% improvement in AUC under the DKT model and the ASSISTmentsChall dataset.</description><identifier>DOI: 10.48550/arxiv.2105.00607</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning</subject><creationdate>2021-05</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2105.00607$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2105.00607$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Lee, Seewoo</creatorcontrib><creatorcontrib>Choi, Youngduck</creatorcontrib><creatorcontrib>Park, Juneyoung</creatorcontrib><creatorcontrib>Kim, Byungsoo</creatorcontrib><creatorcontrib>Shin, Jinwoo</creatorcontrib><title>Consistency and Monotonicity Regularization for Neural Knowledge Tracing</title><description>Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education. In this paper, we present a simple, yet effective strategy to improve the generalization ability of KT models: we propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses that impose certain consistency or monotonicity biases on the model's predictions for the original and augmented sequence. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances, under 3 widely-used neural networks and 4 public benchmarks, e.g., it yields 6.3% improvement in AUC under the DKT model and the ASSISTmentsChall dataset.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUQGEvDKjwAEz4BRJufq7tjFUEFNGChLJH144dWUpt5KRAeHpEYTrbkT7GbgrIa4UId5S-_EdeFoA5gAB5yXZtDLOfFxvMyikM_BBDXGLwxi8rf7PjaaLkv2nxMXAXE3-xp0QTfw7xc7LDaHmXyPgwXrELR9Nsr_-7Yd3Dfdfusv3r41O73WckpMyMaRpZqxKpIFQOrDNWQkMDaSyg1EIAuhJdhVpVirRQUGvjUElBTe1MtWG3f9szpX9P_khp7X9J_ZlU_QA1NkeQ</recordid><startdate>20210502</startdate><enddate>20210502</enddate><creator>Lee, Seewoo</creator><creator>Choi, Youngduck</creator><creator>Park, Juneyoung</creator><creator>Kim, Byungsoo</creator><creator>Shin, Jinwoo</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210502</creationdate><title>Consistency and Monotonicity Regularization for Neural Knowledge Tracing</title><author>Lee, Seewoo ; Choi, Youngduck ; Park, Juneyoung ; Kim, Byungsoo ; Shin, Jinwoo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-cc9974825a1a58f0efce709adab5102b6605f25f35b838ab6804bcf5876a94fc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Lee, Seewoo</creatorcontrib><creatorcontrib>Choi, Youngduck</creatorcontrib><creatorcontrib>Park, Juneyoung</creatorcontrib><creatorcontrib>Kim, Byungsoo</creatorcontrib><creatorcontrib>Shin, Jinwoo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lee, Seewoo</au><au>Choi, Youngduck</au><au>Park, Juneyoung</au><au>Kim, Byungsoo</au><au>Shin, Jinwoo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Consistency and Monotonicity Regularization for Neural Knowledge Tracing</atitle><date>2021-05-02</date><risdate>2021</risdate><abstract>Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education. In this paper, we present a simple, yet effective strategy to improve the generalization ability of KT models: we propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses that impose certain consistency or monotonicity biases on the model's predictions for the original and augmented sequence. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances, under 3 widely-used neural networks and 4 public benchmarks, e.g., it yields 6.3% improvement in AUC under the DKT model and the ASSISTmentsChall dataset.</abstract><doi>10.48550/arxiv.2105.00607</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2105.00607
ispartof
issn
language eng
recordid cdi_arxiv_primary_2105_00607
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
title Consistency and Monotonicity Regularization for Neural Knowledge Tracing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T11%3A32%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Consistency%20and%20Monotonicity%20Regularization%20for%20Neural%20Knowledge%20Tracing&rft.au=Lee,%20Seewoo&rft.date=2021-05-02&rft_id=info:doi/10.48550/arxiv.2105.00607&rft_dat=%3Carxiv_GOX%3E2105_00607%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true