Exploiting Non-Interactive Exercises in Cognitive Diagnosis

Authors: Fangzhou Yao, Qi Liu, Min Hou, Shiwei Tong, Zhenya Huang, Enhong Chen, Jing Sha, Shijin Wang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on realworld datasets demonstrate the supremacy of our framework in long-tailed data. In this section, we first introduce the datasets and our experimental setups. Then, we conduct extensive experiments to answer the following questions:
Researcher Affiliation Collaboration 1Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China 2State Key Laboratory of Cognitive Intelligence 3i FLYTEK AI Research (Central China), i FLYTEK Co., Ltd.
Pseudocode Yes Algorithm 1 Exercise-aware Informative Response Sampling
Open Source Code Yes Our code is available at https://github.com/fannazya/EIRS.
Open Datasets Yes We conduct experiments on two realworld datasets, i.e., ASSISTments1 and Junyi dataset 2. 1https://sites.google.com/site/assistmentsdata/home/2009-2010assistment-data 2https://pslcdatashop.web.cmu.edu/Files?datasetId=1198
Dataset Splits No The paper states, "The number 5 is to ensure that the dataset can be split into train and test sets at an 8:2 ratio." and "all the hyper-parameters are tuned in the validation datasets.", but it does not specify the exact split percentage for the validation set, only the train/test split.
Hardware Specification No The paper does not specify any particular hardware used for experiments, such as GPU or CPU models, memory, or cloud instance types.
Software Dependencies No The paper mentions using the "Adam algorithm" for optimization but does not list specific software dependencies with their version numbers (e.g., Python, PyTorch, TensorFlow versions, or other libraries).
Experiment Setup Yes In our framework, we set the sample number from [1,2,3,4,5]. For the curriculum coefficient λ, its initial value λ0 is chosen from the interval (0, 1], and λ linearly increases from λ0 to 1 as the number of epochs increases. We employ the Adam algorithm [Kingma and Ba, 2015] for optimization, and all the hyper-parameters are tuned in the validation datasets.