SLISEMAP: supervised dimensionality reduction through local explanations
From MaRDI portal
Abstract: Existing methods for explaining black box learning models often focus on building local explanations of model behaviour for a particular data item. It is possible to create global explanations for all data items, but these explanations generally have low fidelity for complex black box models. We propose a new supervised manifold visualisation method, SLISEMAP, that simultaneously finds local explanations for all data items and builds a (typically) two-dimensional global visualisation of the black box model such that data items with similar local explanations are projected nearby. We provide a mathematical derivation of our problem and an open source implementation implemented using the GPU-optimised PyTorch library. We compare SLISEMAP to multiple popular dimensionality reduction methods and find that SLISEMAP is able to utilise labelled data to create embeddings with consistent local white box models. We also compare SLISEMAP to other model-agnostic local explanation methods and show that SLISEMAP provides comparable explanations and that the visualisations can give a broader understanding of black box regression and classification models.
Recommendations
- Considerations when learning additive explanations for black-box models
- Local interpretation of supervised learning models based on high dimensional model representation
- A survey on the explainability of supervised machine learning
- How to explain individual classification decisions
- Interpretation of black-box predictive models
Cites work
- All models are wrong, but many are useful: learning a variable's importance by studying an entire class of prediction models simultaneously
- Conditional t-SNE: more informative t-SNE embeddings
- Detecting virtual concept drift of regressors without ground truth values
- How to explain individual classification decisions
- scientific article; zbMATH DE number 6378173 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 3322635 (Why is no real title available?)
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
- Linear dimensionality reduction: survey, insights, and generalizations
- Local linear regression on manifolds and its geometric interpretation
- Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
- On Divergences and Informations in Statistics and Information Theory
- Robust regression via error tolerance
- Scikit-learn: machine learning in Python
- Updating Quasi-Newton Matrices with Limited Storage
- Visualizing data using t-SNE
This page was built for publication: SLISEMAP: supervised dimensionality reduction through local explanations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097137)
