Wei-Hua Bai

CausalSTKT: Disentangled Spatiotemporal Heterogeneous Graph Learning for Robust Knowledge Tracing Under Distribution Shifts

CausalSTKT is proposed, an SCM-guided knowledge tracing framework that integrates spatiotemporal modeling over a global item–knowledge-component bipartite graph with disentangled representation learning and derives an out-of-distribution risk bound showing that a smaller representation-entanglement residual leads to a...

Causal Benefit-Aware Recommendation for Personalized Learning-Path Features: A Targeting-Policy Framework with Provable Guarantees and Randomized Evaluation

This work formalizes feature recommendation as a causal targeting-policy problem: rank students by the estimated conditional average treatment effect (CATE) of a feature and recommend to the top of the ranking, proving causal top-CATE targeting maximizes policy value at any budget and weakly dominates predictive (outco...

VulGNN: A high-fidelity graph neural network framework for robust smart contract vulnerability detection