Looking Deeper into Tabular LIME

2020-08-25 · Damien Garreau, Ulrike Von Luxburg

In this paper, we present a thorough theoretical analysis of the default implementation of LIME in the case of tabular data. We prove that in the large sample limit, the interpretable coefficients provided by Tabular LIME can be computed in an explicit way as a function of the algorithm parameters and some expectation computations related to the black-box model. When the function to explain has some nice algebraic structure (linear, multiplicative, or sparsely depending on a subset of the coordinates), our analysis provides interesting insights into the explanations provided by LIME. These can be applied to a range of machine learning models including Gaussian kernels or CART random forests. As an example, for linear functions we show that LIME has the desirable property to provide explanations that are proportional to the coefficients of the function to explain and to ignore coordinates that are not used by the function to explain. For partition-based regressors, on the other side, we show that LIME produces undesired artifacts that may provide misleading explanations.

📄 PDF Abstract BibTeX arXiv:2008.11092

Code (1)

dgarreau/tabular_lime_theory 공식 구현

Tasks

BIG-bench Machine Learning

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

TabPFN Through The Looking Glass: An interpretability study of TabPFN and its internal representations

2026-01-13 · Aviral Gupta, Armaan Sethi, Dhruv Kumar arxiv

Tabular foundational models are pre-trained models designed for a wide range of tabular data tasks. They have shown strong performance across domains, yet their internal representations and learned concepts remain poorly…

DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images

2019-10-15 · NeurIPS Workshop Document_Intelligen 2019 12 · W. Ronny Huang, Yike Qi, Qianqian Li, Jonathan Degange

Paper-intensive industries like insurance, law, and government have long leveraged optical character recognition (OCR) to automatically transcribe hordes of scanned documents into text strings for downstream processing. …

Optical Character Recognition Optical Character Recognition (OCR)

bLIMEy: Surrogate Prediction Explanations Beyond LIME

2019-10-29 · Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez, Peter Flach

Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are…

Explainable artificial intelligence Prediction

Enhancing LIME using Neural Decision Trees

2026-03-21 · Mohamed Aymen Bouyahia, Argyris Kalogeratos arxiv

Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanations (LIME) has been a very popular fram…

Interpretable Machine Learning

A unified framework for evaluating the robustness of machine-learning interpretability for prospect risking

2026-02-16 · Prithwijit Chowdhury, Ahmad Mustafa, Mohit Prabhushankar, Ghassan AlRegib arxiv

In geophysics, hydrocarbon prospect risking involves assessing the risks associated with hydrocarbon exploration by integrating data from various sources. Machine learning-based classifiers trained on tabular data have b…