Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces U-GLAD, a novel framework for Learning Path Recommendation (LPR) that addresses historical interaction uncertainty and adapts to diverse learning goals. U-GLAD models cognitive states as probability distributions using a Gaussian LSTM and employs a goal-oriented concept encoder with multi-head attention to align concept semantics with individual learning goals. The framework then uses a generative diffusion model to predict the latent representation of the next optimal concept, outperforming existing methods on three public datasets.
Generative diffusion models can now provide personalized learning path recommendations that outperform traditional ranking approaches by explicitly modeling learner uncertainty and adapting to individual goals.
Learning Path Recommendation (LPR) is critical for personalized education, yet current methods often fail to account for historical interaction uncertainty (e.g., lucky guesses or accidental slips) and lack adaptability to diverse learning goals. We propose U-GLAD (Uncertainty-aware Generative Learning Path Recommendation with Cognition-Adaptive Diffusion). To address representation bias, the framework models cognitive states as probability distributions, capturing the learner's underlying true state via a Gaussian LSTM. To ensure highly personalized recommendation, a goal-oriented concept encoder utilizes multi-head attention and objective-specific transformations to dynamically align concept semantics with individual learning goals, generating uniquely tailored embeddings. Unlike traditional discriminative ranking approaches, our model employs a generative diffusion model to predict the latent representation of the next optimal concept. Extensive evaluations on three public datasets demonstrate that U-GLAD significantly outperforms representative baselines. Further analyses confirm its superior capability in perceiving interaction uncertainty and providing stable, goal-driven recommendation paths.