paper-with-me

Papers

MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Study

2025-03-25 · Shakiba Rahimiaghdam, Hande Alemdar

Ensuring transparency in machine learning decisions is critically important, especially in sensitive sectors such as healthcare, finance, and justice. Despite this, some popular explainable algorithms, such as Local Interpretable Model-agnostic Explanations (LIME), often produce unstable explanations due to the random generation of perturbed samples. Random perturbation introduces small changes or noise to modified instances of the original data, leading to inconsistent explanations. Even slight variations in the generated samples significantly affect the explanations provided by such models, undermining trust and hindering the adoption of interpretable models. To address this challenge, we propose MindfulLIME, a novel algorithm that intelligently generates purposive samples using a graph-based pruning algorithm and uncertainty sampling. MindfulLIME substantially improves the consistency of visual explanations compared to random sampling approaches. Our experimental evaluation, conducted on a widely recognized chest X-ray dataset, confirms MindfulLIME's stability with a 100% success rate in delivering reliable explanations under identical conditions. Additionally, MindfulLIME improves the localization precision of visual explanations by reducing the distance between the generated explanations and the actual local annotations compared to LIME. We also performed comprehensive experiments considering various segmentation algorithms and sample numbers, focusing on stability, quality, and efficiency. The results demonstrate the outstanding performance of MindfulLIME across different segmentation settings, generating fewer high-quality samples within a reasonable processing time. By addressing the stability limitations of LIME in image data, MindfulLIME enhances the trustworthiness and interpretability of machine learning models in specific medical imaging applications, a critical domain.

📄 PDF Abstract BibTeX arXiv:2503.20758

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
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…

Similar Papers 제목 키워드 기반

GLIME: General, Stable and Local LIME Explanation

2023-11-27 · NeurIPS 2023 11 · Zeren Tan, Yang Tian, Jian Li

As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanat…

UbiQVision: Quantifying Uncertainty in XAI for Image Recognition

2025-12-23 · Akshat Dubey, Aleksandar Anžel, Bahar İlgen, Georges Hattab arxiv

Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is driven by increasingly sophisticated model architectures, such as ResNets, Vision T…

Robust and Stable Black Box Explanations

2020-11-12 · Himabindu Lakkaraju, Nino Arsov, Osbert Bastani

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black boxes. However…

Cover Filtration and Stable Paths in the Mapper

2019-09-25 · Dustin L. Arendt, Matthew Broussard, Bala Krishnamoorthy, Nathaniel Saul

The contributions of this paper are two-fold. We define a new filtration called the cover filtration built from a single cover based on a generalized Steinhaus distance, which is a generalization of Jaccard distance. We …

BIG-bench Machine LearningRecommendation Systems

EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations

2024-02-01 · Aditya Bhattacharya, Simone Stumpf, Lucija Gosak, Gregor Stiglic 외

Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric and data-centric explanations in aiding domain experts…