MeLIME: Meaningful Local Explanation for Machine Learning Models
By T. Botari, Frederik Hvilshoj, Rafael Izbicki, André Carlos Ponce de Leon Ferreira de Carvalho. 2020
21 citations recorded by the source corpus.
Most state-of-the-art machine learning algorithms induce black-box models, preventing their application in many sensitive domains. Hence, many methodologies for explaining machine learning models have been proposed to address this problem. In this work, we introduce strategies to improve local explanations taking into account the distribution of the data used to train the black-box models. We show that our approach, MeLIME, produces more meaningful explanations compared to other techniques over different ML models, operating on various types of data. MeLIME generalizes the LIME method, allowing more flexible perturbation sampling and the use of different local interpretable models. Additionally, we introduce modifications to standard training algorithms of local interpretable models fostering more robust explanations, even allowing the production of counterfactual examples. To show the strengths of the proposed approach, we include experiments on tabular data, images, and text; all showing improved explanations. In particular, MeLIME generated more meaningful explanations on the MNIST dataset than methods such as GuidedBackprop, SmoothGrad, and Layer-wise Relevance Propagation. MeLIME is available on this https URL.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Emilio Carrizosa
- Dolores Romero Morales
- Cristina Molero-Río
- Christoph Molnar
- Giuseppe Casalicchio
- Bernd Bischl
- Cynthia Rudin
- Berk Ustun
Citations in the corpus
- Mathematical optimization in classification and regression trees (2021, positive): “…number of shortcomings to this approach around, for instance, the generation of data or the loss of accuracy, which have been addressed with enhancements (Botari et al. 2020; Visani et al. 2020; Zhang et al. 2019), or with alternative approaches (Lundberg et al. 2020, 2018; Lundberg and Lee 2017).”
- Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges (2020, methodology): “Numerous extensions of LIME exist, which try to fix issues with the original method, extend it to other tasks and data, or analyze its properties [53,93,92,121,47,94,103,12].”