Optimizing Bayesian Knowledge Tracing with Neural Network Parameter Generation
Saved in:
| Title: | Optimizing Bayesian Knowledge Tracing with Neural Network Parameter Generation |
|---|---|
| Language: | English |
| Authors: | Anirudhan Badrinath, Zachary Pardos |
| Source: | Journal of Educational Data Mining. 2025 17(1):41-65. |
| Availability: | International Educational Data Mining. e-mail: jedm.editor@gmail.com; Web site: https://jedm.educationaldatamining.org/index.php/JEDM |
| Peer Reviewed: | Y |
| Page Count: | 25 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Reports - Research |
| Descriptors: | Bayesian Statistics, Intelligent Tutoring Systems, Problem Solving, Audience Response Systems, Learning Processes, Item Response Theory, Predictive Measurement, Test Validity, Test Reliability |
| ISSN: | 2157-2100 |
| Abstract: | Bayesian Knowledge Tracing (BKT) is a well-established model for formative assessment, with optimization typically using expectation maximization, conjugate gradient descent, or brute force search. However, one of the flaws of existing optimization techniques for BKT models is convergence to undesirable local minima that negatively impact performance and interpretability of the BKT parameters (i.e., parameter degeneracy). Recently, deep knowledge tracing methods such as context-aware attentive knowledge tracing have proven to be state-of-the-art in performance; however, these methods often lack the inherent interpretability or understanding provided by BKT's skill-level parameter estimates and student-level mastery probability estimates. We propose a novel optimization technique for BKT models using a neural network-based parameter generation approach, OptimNN, that leverages hypernetworks and stochastic gradient descent for training BKT parameters. We extend this approach and propose BK Transformer, a transformer-based sequence modeling technique that generates temporally-evolving BKT parameters for student response correctness prediction. With both approaches, we demonstrate improved performance compared to BKT and deep KT baselines, with minimal hyperparameter tuning. Importantly, we demonstrate that these techniques, despite their state-of-the-art expressive capability, retain the interpretability of skill-level BKT parameter estimates and student-level estimates of mastery and correctness probabilities. [The page range cited on the .pdf (p1-25) is incorrect. The correct page range is p41-65.] |
| Abstractor: | As Provided |
| Notes: | https://github.com/abadrinath947/OptimNN |
| Entry Date: | 2025 |
| Accession Number: | EJ1458433 |
| Database: | ERIC |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1458433 Name: ERIC Full Text Category: fullText Text: Full Text from ERIC |
|---|---|
| Header | DbId: eric DbLabel: ERIC An: EJ1458433 AccessLevel: 3 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Optimizing Bayesian Knowledge Tracing with Neural Network Parameter Generation – Name: Language Label: Language Group: Lang Data: English – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Anirudhan+Badrinath%22">Anirudhan Badrinath</searchLink><br /><searchLink fieldCode="AR" term="%22Zachary+Pardos%22">Zachary Pardos</searchLink> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="SO" term="%22Journal+of+Educational+Data+Mining%22"><i>Journal of Educational Data Mining</i></searchLink>. 2025 17(1):41-65. – Name: Avail Label: Availability Group: Avail Data: International Educational Data Mining. e-mail: jedm.editor@gmail.com; Web site: https://jedm.educationaldatamining.org/index.php/JEDM – Name: PeerReviewed Label: Peer Reviewed Group: SrcInfo Data: Y – Name: Pages Label: Page Count Group: Src Data: 25 – Name: DatePubCY Label: Publication Date Group: Date Data: 2025 – Name: TypeDocument Label: Document Type Group: TypDoc Data: Journal Articles<br />Reports - Research – Name: Subject Label: Descriptors Group: Su Data: <searchLink fieldCode="DE" term="%22Bayesian+Statistics%22">Bayesian Statistics</searchLink><br /><searchLink fieldCode="DE" term="%22Intelligent+Tutoring+Systems%22">Intelligent Tutoring Systems</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+Solving%22">Problem Solving</searchLink><br /><searchLink fieldCode="DE" term="%22Audience+Response+Systems%22">Audience Response Systems</searchLink><br /><searchLink fieldCode="DE" term="%22Learning+Processes%22">Learning Processes</searchLink><br /><searchLink fieldCode="DE" term="%22Item+Response+Theory%22">Item Response Theory</searchLink><br /><searchLink fieldCode="DE" term="%22Predictive+Measurement%22">Predictive Measurement</searchLink><br /><searchLink fieldCode="DE" term="%22Test+Validity%22">Test Validity</searchLink><br /><searchLink fieldCode="DE" term="%22Test+Reliability%22">Test Reliability</searchLink> – Name: ISSN Label: ISSN Group: ISSN Data: 2157-2100 – Name: Abstract Label: Abstract Group: Ab Data: Bayesian Knowledge Tracing (BKT) is a well-established model for formative assessment, with optimization typically using expectation maximization, conjugate gradient descent, or brute force search. However, one of the flaws of existing optimization techniques for BKT models is convergence to undesirable local minima that negatively impact performance and interpretability of the BKT parameters (i.e., parameter degeneracy). Recently, deep knowledge tracing methods such as context-aware attentive knowledge tracing have proven to be state-of-the-art in performance; however, these methods often lack the inherent interpretability or understanding provided by BKT's skill-level parameter estimates and student-level mastery probability estimates. We propose a novel optimization technique for BKT models using a neural network-based parameter generation approach, OptimNN, that leverages hypernetworks and stochastic gradient descent for training BKT parameters. We extend this approach and propose BK Transformer, a transformer-based sequence modeling technique that generates temporally-evolving BKT parameters for student response correctness prediction. With both approaches, we demonstrate improved performance compared to BKT and deep KT baselines, with minimal hyperparameter tuning. Importantly, we demonstrate that these techniques, despite their state-of-the-art expressive capability, retain the interpretability of skill-level BKT parameter estimates and student-level estimates of mastery and correctness probabilities. [The page range cited on the .pdf (p1-25) is incorrect. The correct page range is p41-65.] – Name: AbstractInfo Label: Abstractor Group: Ab Data: As Provided – Name: Note Label: Notes Group: Note Data: https://github.com/abadrinath947/OptimNN – Name: DateEntry Label: Entry Date Group: Date Data: 2025 – Name: AN Label: Accession Number Group: ID Data: EJ1458433 |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1458433 |
| RecordInfo | BibRecord: BibEntity: Languages: – Text: English PhysicalDescription: Pagination: PageCount: 25 StartPage: 41 Subjects: – SubjectFull: Bayesian Statistics Type: general – SubjectFull: Intelligent Tutoring Systems Type: general – SubjectFull: Problem Solving Type: general – SubjectFull: Audience Response Systems Type: general – SubjectFull: Learning Processes Type: general – SubjectFull: Item Response Theory Type: general – SubjectFull: Predictive Measurement Type: general – SubjectFull: Test Validity Type: general – SubjectFull: Test Reliability Type: general Titles: – TitleFull: Optimizing Bayesian Knowledge Tracing with Neural Network Parameter Generation Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Anirudhan Badrinath – PersonEntity: Name: NameFull: Zachary Pardos IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2025 Identifiers: – Type: issn-electronic Value: 2157-2100 Numbering: – Type: volume Value: 17 – Type: issue Value: 1 Titles: – TitleFull: Journal of Educational Data Mining Type: main |
| ResultId | 1 |
