Skip to content

Open-source PyTorch DKT implementation

Product or Programme · All products and programmes
Evidence · 1 claim (1 mixed) · 2 studies (2 causal), q2 · 0 of 2 report an effect size

Description

An open-source PyTorch implementation created by the article's authors for fitting Deep Knowledge Tracing to DataShop-format data and using it in online knowledge-tracing settings.

Components

  • Open-source PyTorch DKT implementation supporting online knowledge tracing with DataShop-format data: The authors created their own DKT implementation using PyTorch's LSTM module to support online mastery learning. Based on prior work, "the model has 200 nodes in the hidden layer, uses a dropout of 0.4 during training, and uses a batch size of 5." It "supports the ability to fit DKT to data presented in standard DataShop format" and provides "a simple interface for use in online knowledge tracing settings." Open-source code is available at the authors' GitLab repository. (Going Online: A Simulated Student Approach for Evaluating Knowledge Tracing in the Context)
  • DKT released code and preprocessed data: To facilitate research on deep knowledge tracing, the authors published their model code and preprocessed datasets on GitHub. The article states: "To facilitate research in DKTs we have published our code and relevant preprocessed data" at the repository chrispiech/DeepKnowledgeTracing. This release supports replication of the LSTM/RNN knowledge tracing results and reuse of the training pipeline in follow-up work. (Chris Piech et al. (2015))

Claims

-

Key Sources

  • Qiao Zhang and Christopher MacLellan “Going Online: A simulated student approach for evaluating knowledge tracing in the context of mastery learning”. 2021. In: Proceedings of The 14th International Conference on Educational Data Mining (EDM21). International Educational Data Mining Society, 331-337. https://educationaldatamining.org/edm2021/
Page metadata
Field Value
type product
id open-source-pytorch-dkt-implementation
title Open-source PyTorch DKT implementation
description An open-source PyTorch implementation created by the article's authors for fitting Deep Knowledge Tracing to DataShop-format data and using it in online knowledge-tracing settings.
status review
moved_from element/pytorch-dkt-online-implementation
product_kind software
generated by process:sweep-kinds on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — qiao-zhang-and-christopher-maclellan

Frontmatter is the page's machine-readable record — see the Schema & Guide.