Interpreting Multivariate Shapley Interactions in DNNs

Authors: Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang10877-10886

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have conducted experiments with various DNNs. Experimental results have demonstrated the effectiveness of the proposed method.
Researcher Affiliation Academia Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang Shanghai Jiao Tong University, China {1603023-zh,xieyichen,bugatti,zizhan52,zqs1022}@sjtu.edu.cn
Pseudocode No The paper describes the method and uses mathematical equations but does not present structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about open-sourcing code or direct links to code repositories.
Open Datasets Yes binary sentiment classification based on the SST-2 dataset (Socher et al. 2013) and prediction of linguistic acceptability based on the Co LA dataset (Warstadt, Singh, and Bowman 2018).
Dataset Splits No The paper references the SST-2 and CoLA datasets but does not explicitly provide specific training, validation, or test split percentages or counts for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We found that the estimated significance of interactions was accurate enough after the training of 100 epochs.