Pith. sign in

REVIEW 2 cited by

A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2002.07434 v1 pith:NDDMPX5X submitted 2020-02-18 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords explanationinterpretablelimemps-limeperturbedsamplingimagelearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Explainability is a gateway between Artificial Intelligence and society as the current popular deep learning models are generally weak in explaining the reasoning process and prediction results. Local Interpretable Model-agnostic Explanation (LIME) is a recent technique that explains the predictions of any classifier faithfully by learning an interpretable model locally around the prediction. However, the sampling operation in the standard implementation of LIME is defective. Perturbed samples are generated from a uniform distribution, ignoring the complicated correlation between features. This paper proposes a novel Modified Perturbed Sampling operation for LIME (MPS-LIME), which is formalized as the clique set construction problem. In image classification, MPS-LIME converts the superpixel image into an undirected graph. Various experiments show that the MPS-LIME explanation of the black-box model achieves much better performance in terms of understandability, fidelity, and efficiency.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning

    cs.LG 2025-06 conditional novelty 5.0 of 10

    DL-LIME replaces independent LIME perturbations with a DNN-generated correlated feature sampling and improves explanation fidelity and task utility for a DDPG-based radar resource manager compared with conventional LIME.

  2. MUPAX: Multidimensional Problem Agnostic eXplainable AI

    cs.LG 2025-07 reject novelty 4.0 of 10

    MUPAX's feature importance is a weighted average of masked inputs selected for low loss, and its accuracy gains stem from using ground-truth labels during mask selection.

Pith tools