loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Yahya Badran 1 ; 2 and Christine Preisach 1 ; 2

Affiliations: 1 Karlsruhe University of Education, Bismarckstr 10,76133 Karlsruhe, Germany ; 2 Karlsruhe University of Applied Sciences, Moltekstr. 30, 76133 Karlsruhe, Germany

Keyword(s): Knowledge Tracing, Knowledge Concepts, Data Leakage, Intelligent Tutoring Systems, Sparsity, Deep Learning.

Abstract: Knowledge Tracing (KT) is concerned with predicting students’ future performance on learning items in intelligent tutoring systems. Learning items are tagged with skill labels called knowledge concepts (KCs). Many KT models expand the sequence of item-student interactions into KC-student interactions by replacing learning items with their constituting KCs. This approach addresses the issue of sparse item-student interactions and minimises the number of model parameters. However, we identified a label leakage problem with this approach. The model’s ability to learn correlations between KCs belonging to the same item can result in the leakage of ground truth labels, which leads to decreased performance, particularly on datasets with a high number of KCs per item. In this paper, we present methods to prevent label leakage in knowledge tracing (KT) models. Our model variants that utilize these methods consistently outperform their original counterparts. This further underscores the impac t of label leakage on model performance. Additionally, these methods enhance the overall performance of KT models, with one model variant surpassing all tested baselines on different benchmarks. Notably, our methods are versatile and can be applied to a wide range of KT models. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.191.154.119

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Badran, Y. and Preisach, C. (2025). Addressing Label Leakage in Knowledge Tracing Models. In Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU; ISBN 978-989-758-746-7; ISSN 2184-5026, SciTePress, pages 85-95. DOI: 10.5220/0013275200003932

@conference{csedu25,
author={Yahya Badran and Christine Preisach},
title={Addressing Label Leakage in Knowledge Tracing Models},
booktitle={Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU},
year={2025},
pages={85-95},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013275200003932},
isbn={978-989-758-746-7},
issn={2184-5026},
}

TY - CONF

JO - Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU
TI - Addressing Label Leakage in Knowledge Tracing Models
SN - 978-989-758-746-7
IS - 2184-5026
AU - Badran, Y.
AU - Preisach, C.
PY - 2025
SP - 85
EP - 95
DO - 10.5220/0013275200003932
PB - SciTePress