A study of data and label shift in the LIME framework
LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero features of the predicted instance. After that, the perturbed instances are fed into the black-box model to obtain labels for these, which are then used for training the interpretable model. In this study, we present a systematic evaluation of the interpretable models that are output by LIME on the two use-cases that were considered in the original paper introducing the approach; text classification and object detection. The investigation shows that the perturbation and labeling phases result in both data and label shift. In addition, we study the correlation between the shift and the fidelity of the interpretable model and show that in certain cases the shift negatively correlates with the fidelity. Based on these findings, it is argued that there is a need for a new sampling approach that mitigates the shift in the LIME's framework.
Code (0)
등록된 구현이 없습니다.
Tasks
object-detectionObject Detectiontext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Explainable Misinformation Detection Across Multiple Social Media Platforms
In this work, the integration of two machine learning approaches, namely domain adaptation and explainable AI, is proposed to address these two issues of generalized detection and explainability. Firstly the Domain Adver…
Domain AdaptationMisinformationEffect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data
End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approac…
image-classificationImage ClassificationSuperpixelsLIME: Weakly-Supervised Text Classification Without Seeds
In weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framework, where test samples are first assign…
ClassificationNatural Language Inferencetext-classificationText Classification+1Diffusion Model based Semi-supervised Learning on Brain Hemorrhage Images for Efficient Midline Shift Quantification
Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage. Existing computational methods on MLS quantification not on…
Decision MakingRepresentation LearningUsing a Local Surrogate Model to Interpret Temporal Shifts in Global Annual Data
This paper focuses on explaining changes over time in globally-sourced, annual temporal data, with the specific objective of identifying pivotal factors that contribute to these temporal shifts. Leveraging such analytica…
Feature Importancefeature selectionImputationMissing Values+1