Dual feature-based and example-based explanation methods
This work addresses the need for improved interpretability in ML models, offering a novel method for generating feature-based and example-based explanations, though it appears incremental as a modification of LIME.
The authors tackled the problem of local and global explanation in machine learning by proposing a dual representation approach using convex hulls and convex combinations, which achieved explanation through dual linear surrogate models and neural additive models, with code provided for reproducibility.
A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of instances in the form of convex combinations of extreme points of a produced polytope. Instead of perturbing new instances in the Euclidean feature space, vectors of convex combination coefficients are uniformly generated from the unit simplex, and they form a new dual dataset. A dual linear surrogate model is trained on the dual dataset. The explanation feature importance values are computed by means of simple matrix calculations. The approach can be regarded as a modification of the well-known model LIME. The dual representation inherently allows us to get the example-based explanation. The neural additive model is also considered as a tool for implementing the example-based explanation approach. Many numerical experiments with real datasets are performed for studying the approach. The code of proposed algorithms is available.