Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation

Authors: zheng zhang, Wei Song, Qi Liu, Qingyang Mao, Yiyan Wang, Weibo Gao, Zhenya Huang, Shijin Wang, Enhong Chen

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, extensive experiments on real-world datasets showcase the efficacy of our framework in addressing the data sparsity issue with accurate and fair CD results.
Researcher Affiliation Collaboration 1: University of Science and Technology of China 2: State Key Laboratory of Cognitive Intelligence 3: Beijing Normal University {zhangzheng,sw2,maoqy0503,weibogao}@mail.ustc.edu.cn; {qiliuql,huangzhy,cheneh}@ustc.edu.cn; wangyiyan@mail.bnu.edu.cn; sjwang3@ifytek.com
Pseudocode No The paper describes the proposed framework and method verbally and mathematically but does not include any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes The code is released at https://github.com/Mercidaiha/CMCD.
Open Datasets Yes The ASSIST dataset (ASSISTments 2009-2010 skill builder") is an open dataset collected by the ASSISTments online tutoring systems [12]
Dataset Splits No Regarding the dataset division, we allocate 80% of each student s response log for training and the remaining 20% for testing. There is no explicit mention of a separate validation split percentage or size within the experimental setup details.
Hardware Specification Yes We implement all models with Py Torch and conduct all experiments on four 2.0GHz Intel Xeon E5-2620 CPUs and a Tesla K20m GPU.
Software Dependencies No We implement all models with Py Torch. No specific version number for PyTorch or other software dependencies is provided.
Experiment Setup Yes For all models, we set the learning rate to 0.001 and the dropout rate to 0.2. We apply Adam as the optimization algorithm to update the model parameters.