PredictiveEigenSimplicial

PredictiveEigenSimplicial A Graph Neural Network enhanced framework for personalized curriculum learning path recommendation and dynamic adaptation. Overview PredictiveEigenSimplicial is a personalized learning path recommendation method that uses Graph Neural Networks (GNNs) to model learner progress, curriculum structures, prerequisite relations, and higher-order educational interactions. The framework integrates three key modules: - Predictive Coding Integrator: captures temporal and sequential learning behavior.- Eigen Interaction Filter: extracts harmonic and global structural relationships.- Simplicial Structure Mapper: models higher-order interactions among learners, concepts, resources, and assessments. The method dynamically adapts recommended learning paths according to learners’ evolving performance, preferences, and future learning needs. Features - Personalized curriculum learning path recommendation- Dynamic adaptation based on learner state changes- Graph-based prerequisite and curriculum modeling- Higher-order simplicial interaction modeling- Harmonic relation extraction using spectral graph structures- Improved recommendation accuracy and learning outcome prediction Project Structure ├── data/ # Dataset files├── models/ # Model implementations├── scripts/ # Training and evaluation scripts├── configs/ # Experiment configurations├── results/ # Logs and output metrics└── README.mdInstallationgit clone https://github.com/your-username/PredictiveEigenSimplicial.gitcd PredictiveEigenSimplicial pip install -r requirements.txtUsagepython scripts/train.py --config configs/default.yamlTo evaluate a trained model: python scripts/evaluate.py --checkpoint path/to/checkpoint.ptCitation@article{predictiveeigensimplicial, title={Graph Neural Network Enhanced Personalized Curriculum Learning Path Recommendation and Dynamic Adaptation Method}, author={Du, Guobiao and Qiu, Feiyue and He, Tao and Guo, Haidong and Wang, Liping}, year={2025}}