paper-with-me

홈 › Papers

Improving LIME Robustness with Smarter Locality Sampling

2020-06-22 · Sean Saito, Eugene Chua, Nicholas Capel, Rocco Hu

Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases. However, recent work has shown that LIME's naive sampling strategy can be exploited by an adversary to conceal biased, harmful behavior. We propose to make LIME more robust by training a generative adversarial network to sample more realistic synthetic data which the explainer uses to generate explanations. Our experiments demonstrate that our proposed method demonstrates an increase in accuracy across three real-world datasets in detecting biased, adversarial behavior compared to vanilla LIME. This is achieved while maintaining comparable explanation quality, with up to 99.94\% in top-1 accuracy in some cases.

📄 PDF Abstract BibTeX arXiv:2006.12302

Code (1)

seansaito/Faster-LIME 공식 구현

Tasks

FairnessGenerative Adversarial Network

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…

Similar Papers 제목 키워드 기반

RoPE-LIME: RoPE-Space Locality + Sparse-K Sampling for Efficient LLM Attribution

2026-02-06 · Isaac Picov, Ritesh Goru arxiv

Explaining closed-source Large Language Model (LLM) outputs is challenging because API access prevents gradient-based attribution, while perturbation methods are costly and noisy when they depend on regenerated text. We …

s-LIME: Reconciling Locality and Fidelity in Linear Explanations

2022-08-02 · Romaric Gaudel, Luis Galárraga, Julien Delaunay, Laurence Rozé 외

The benefit of locality is one of the major premises of LIME, one of the most prominent methods to explain black-box machine learning models. This emphasis relies on the postulate that the more locally we look at the vic…

ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings

2025-08-19 · Rehan Raza, Guanjin Wang, Kok Wai Wong, Hamid Laga 외 arxiv

Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior l…

Contrastive LearningTransfer Learning

On Locality of Local Explanation Models

2021-06-24 · NeurIPS 2021 12 · Sahra Ghalebikesabi, Lucile Ter-Minassian, Karla Diaz-Ordaz, Chris Holmes

Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature absence under a global population distribution. The use of a global population can lead to poten…

audioLIME: Listenable Explanations Using Source Separation

2020-08-02 · Verena Haunschmid, Ethan Manilow, Gerhard Widmer

Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method based on Local Interpr…

Information RetrievalMusic Information RetrievalMusic TaggingRetrieval