EduStudio
EduStudio is a Unified Library for Student Cognitive Modeling including Cognitive Diagnosis(CD) and Knowledge Tracing(KT) based on Pytorch.
Modularized & Templatized
EduStudio first decomposes the general algorithmic workflow into six modules: configuration reading, data preparation, model implementation, training control, model evaluation, and log storage.
Subsequently, to enhance the reusability and scalability of each step, EduStudio extracts the commonalities of each algorithm at each step into individual templates for templatization.
- Unification for CD and KT
- Modularization
- Templatization
Leaderboard
To ensure the reproducibility and fair comparision of various student cognitive modeling models, we provide a public leaderboard.
- Support Multiple Scenarios
- Automatic Development Workflow
- Support Uploading Your Own Experiment
Templatization
The highly-templatization greatly enhances the scalability and reusability of EduStudio. This enables users to select and reuse the corresponding templates as needed.
Unification for CD and KT
The unification of CD and KT for student assessment models not only reuse their commonality but also follow an existing trend.
User-friendly Utilities
The various utilities (such as callback and data cache) in EduStudio greatly enhance the convenience for researchers.
Easy-of-use
The quick start function is convenient for newbies who are not familiar with EduStudio.
Comprehensive Eco-Services
We provide comprehensive eco-services including Eco-Leaderboard and Eco-Repository
Keep up-to-date
EduStudio always keeps up-to-date. we will continually improve the usage of EduStudio toolkit and add new student assessment models to facilitate the community.