AMBER
An adaptive meta-balancing framework for integrating heterogeneous graph signals in knowledge tracing.
Learning-state estimation
Knowledge Tracing
We study models of learner knowledge that account for uncertainty, heterogeneous graph structure, and interpretability. This area brings together the AMBER and UKT implementations with their publication records so researchers can move from a method overview to the primary evidence and reproduction materials.
Projects and implementations
2 worksUKT
Uncertainty-aware knowledge tracing that represents student states as distributions instead of fixed deterministic embeddings.
Publications
3 papersInterpretable Knowledge Tracing via Explicit-Implicit Alignment
E Ni, J Wang, J Luan, et al.
AMBER: Adaptive Meta Balanced Paradigm for Heterogeneous Graph-Based Knowledge Tracing
L Sun, Z Yuan, E Ni, et al.
Uncertainty-Aware Knowledge Tracing
W Cheng, H Du, C Li, et al.