EUVIMEDEUVIMED entdecken
Crossref

Enhancing Knowledge Tracing via Breakpoint-Aware Sequence Augmentation

Chunli Huang, Wenjun Jiang, Kenli Li, Ji Zhang, Jie Wu

IEEE Transactions on Knowledge and Data Engineering · 2026-08 · 38 (8) · 5062-5076

DOI: 10.1109/tkde.2026.3700199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-08. Verfasst von Chunli Huang und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Provincial Natural Science Foundation of Hunan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge Tracing (KT) aims to predict learners’ future responses by modeling historical learning sequences. However, existing works often overlook the severe disruptions in temporal and interaction continuity arising from large time intervals between interactions, which leads to significant prediction errors. Therefore, we identify and validate this breakpoint effect through empirical studies, and try to address it via data augmentation (DA). Existing DA methods usually emphasize sequence diversity or similarity while neglecting the breakpoint effect in KT. Hence, we strive to enhance knowledge tracing via breakpoint-aware sequence augmentation and propose Collaborative Learning Path Augmentation (CLPA), a systematic three-phase method to enhance models’ representational capacity and alleviate the breakpoint effects. First, identifying boundary interaction pairs that exhibit the temporal gap and response inconsistency. Second, leveraging cross-sequence collaborative information to infer functional pseudo-paths between identified boundaries. Third, reconstructing and inserting pseudo-learning paths into target sequences to restore sequence continuity; moreover, two refinements of the sampling quantity constraint and the distance-based sampling strategy are proposed to ensure augmentation quality. Comprehensive experiments on four real-world datasets validate the effectiveness of CLPA, which significantly enhances the target KT model’s representational capacity and alleviates the breakpoint effects.

Förderung

  • National Natural Science Foundation of China
  • Provincial Natural Science Foundation of Hunan

Zitieren

APA

Huang, C., Jiang, W., Li, K., Zhang, J., & Wu, J. (2026). Enhancing Knowledge Tracing via Breakpoint-Aware Sequence Augmentation. IEEE Transactions on Knowledge and Data Engineering, 38(8), 5062-5076. https://doi.org/10.1109/tkde.2026.3700199

Vancouver

Huang C, Jiang W, Li K, Zhang J, Wu J. Enhancing Knowledge Tracing via Breakpoint-Aware Sequence Augmentation. IEEE Transactions on Knowledge and Data Engineering. 2026;38(8):5062-5076. doi:10.1109/tkde.2026.3700199

BibTeX
@article{Huang2026,
  author = {Huang, Chunli and Jiang, Wenjun and Li, Kenli and Zhang, Ji and Wu, Jie},
  title = {Enhancing Knowledge Tracing via Breakpoint-Aware Sequence Augmentation},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {8},
  pages = {5062--5076},
  doi = {10.1109/tkde.2026.3700199}
}
Kostenlos starten →