.png){kind=icon}
.png){kind=icon}
Return
Learning multi-granularity temporal characteristics for attention based knowledge tracing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.131338.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• MTKT captures multi-granular temporal features from student interactions. • A linear decay bias handles variable sequence lengths and irregular time intervals. • Causal interaction convolution models both short- and long-term learning patterns. • MTKT outperforms 14 baseline models in predictive performance.
Keywords:
MTKT
temporal features
linear decay bias
causal interaction convolution
predictive performance
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W