Shapley explainability on the data manifold

Authors: Christopher Frye, Damien de Mijolla, Tom Begley, Laurence Cowton, Megan Stanley, Ilya Feige

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the effectiveness of these methods on higher-dimensional data with experiments. ... In this section, we perform additional experiments to study the performance and stability of Sec. 4.1 s methods, as well as their effectiveness on higher-dimensional data.
Researcher Affiliation Industry Christopher Frye, Damien de Mijolla, Tom Begley, Laurence Cowton, Megan Stanley, Ilya Feige Faculty, 54 Welbeck Street, London, UK
Pseudocode No The paper does not include any pseudocode or explicitly labeled algorithm blocks.
Open Source Code No The paper mentions using the SHAP package and sklearn, but does not provide a statement or link for the open-sourcing of their own methodology's code.
Open Datasets Yes We can demonstrate this on UCI Census Income data (Dua & Graff, 2017). ... We can demonstrate this on UCI Drug Consumption data (Dua & Graff, 2017). ... We can demonstrate this on real data using UCI Abalone data (Dua & Graff, 2017). ... For binary MNIST (Le Cun & Cortes, 2010), we trained a fully connected network...
Dataset Splits No For each experiment in this paper, we tuned hyperparameters to minimise the MSE of Eq. (16) on a held-out validation set; see App. B for numerical details. ... We split the dataset between 99% inliers and 1% outliers, with the classes generated according to: ... The paper mentions 'test set accuracy' and 'held-out validation set' but does not specify the exact percentages or sample counts for the train/validation/test splits for the main datasets (UCI, MNIST).
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 mentions using 'sklearn parameters' and the 'SHAP package', and references 'Adam (Kingma & Ba, 2015)' for optimization, but does not provide specific version numbers for these software dependencies.
Experiment Setup Yes All neural networks in this paper used 2 flat hidden layers, Adam (Kingma & Ba, 2015) for optimisation, and a batch size of 256. ... We scanned over a grid with hidden layer size = {128, 256, 512} learning rate = {10-3, 10-4} choosing the point with minimal MSE on a held-out validation set after 10k epochs of training; see Table 2. ... Table 2: Optimal hyperparameters found for computing on-manifold Shapley values.