Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models

• URL: http://arxiv.org/abs/2001.11757v2
• Date: Thu, 12 Nov 2020 09:30:09 GMT
• Title: Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models
• Authors: Giorgio Visani, Enrico Bagli, Federico Chesani, Alessandro Poluzzi and Davide Capuzzo
• Abstract summary: The ever increasing usage of Machine Learning techniques is the clearest example of such trend. It is very difficult to understand on what grounds the algorithm took the decision. It is important for the practitioner to be aware of the issue, as well as to have a tool for spotting it.
• Score: 60.67142194009297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nowadays we are witnessing a transformation of the business processes towards a more computation driven approach. The ever increasing usage of Machine Learning techniques is the clearest example of such trend. This sort of revolution is often providing advantages, such as an increase in prediction accuracy and a reduced time to obtain the results. However, these methods present a major drawback: it is very difficult to understand on what grounds the algorithm took the decision. To address this issue we consider the LIME method. We give a general background on LIME then, we focus on the stability issue: employing the method repeated times, under the same conditions, may yield to different explanations. Two complementary indices are proposed, to measure LIME stability. It is important for the practitioner to be aware of the issue, as well as to have a tool for spotting it. Stability guarantees LIME explanations to be reliable, therefore a stability assessment, made through the proposed indices, is crucial. As a case study, we apply both Machine Learning and classical statistical techniques to Credit Risk data. We test LIME on the Machine Learning algorithm and check its stability. Eventually, we examine the goodness of the explanations returned.

Related papers

• Does More Inference-Time Compute Really Help Robustness? [50.47666612618054]
  We show that small-scale, open-source models can benefit from inference-time scaling.<n>We identify an important security risk, intuitively motivated and empirically verified as an inverse scaling law.<n>We urge practitioners to carefully weigh these subtle trade-offs before applying inference-time scaling in security-sensitive, real-world applications.
  arXiv  Detail & Related papers  (2025-07-21T18:08:38Z)
• Scalability of memorization-based machine unlearning [2.5782420501870296]
  Machine unlearning (MUL) focuses on removing the influence of specific subsets of data from pretrained models. Memorization-based unlearning methods have been developed, demonstrating exceptional performance with respect to unlearning quality. We tackle these scalability challenges of state-of-the-art memorization-based MUL algorithms using a series of memorization-score proxies.
  arXiv  Detail & Related papers  (2024-10-21T21:18:39Z)
• Improving Data-aware and Parameter-aware Robustness for Continual Learning [3.480626767752489]
  This paper analyzes that this insufficiency arises from the ineffective handling of outliers. We propose a Robust Continual Learning (RCL) method to address this issue. The proposed method effectively maintains robustness and achieves new state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2024-05-27T11:21:26Z)
• Preservation of Feature Stability in Machine Learning Under Data Uncertainty for Decision Support in Critical Domains [0.0]
  Decision-making in human activities often relies on incomplete data, even in critical domains. This paper addresses this gap by conducting a set of experiments using traditional machine learning methods. We found that the ML descriptive approach maintains higher classification accuracy while ensuring the stability of feature selection as data incompleteness increases.
  arXiv  Detail & Related papers  (2024-01-19T22:11:54Z)
• Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
  Underlying data structures are often exploited to improve the solution of learning tasks. Data augmentation induces these symmetries during training by applying multiple transformations to the input data. This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
  arXiv  Detail & Related papers  (2022-09-29T18:11:01Z)
• Evaluating Machine Unlearning via Epistemic Uncertainty [78.27542864367821]
  This work presents an evaluation of Machine Unlearning algorithms based on uncertainty. This is the first definition of a general evaluation of our best knowledge.
  arXiv  Detail & Related papers  (2022-08-23T09:37:31Z)
• Just Another Method to Compute MTTF from Continuous Time Markov Chain [0.0]
  The Meantime to Failure is a statistic used to determine how much time a system spends to enter one of its absorption states. This work presents a method to obtain the Meantime to Failure from a Continuous Time Markov Chain models.
  arXiv  Detail & Related papers  (2022-02-01T14:21:25Z)
• MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms [82.90843777097606]
  We propose a causally-aware imputation algorithm (MIRACLE) for missing data. MIRACLE iteratively refines the imputation of a baseline by simultaneously modeling the missingness generating mechanism. We conduct extensive experiments on synthetic and a variety of publicly available datasets to show that MIRACLE is able to consistently improve imputation.
  arXiv  Detail & Related papers  (2021-11-04T22:38:18Z)
• OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms [2.570261777174546]
  Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. LIME is widespread across different domains, although its instability is one of the major shortcomings. We propose a framework to maximise stability, while retaining a predefined level of adherence.
  arXiv  Detail & Related papers  (2020-06-10T08:10:37Z)
• DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction [96.90215318875859]
  We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from corrective feedback. We propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training.
  arXiv  Detail & Related papers  (2020-03-16T16:18:52Z)
• Hidden Cost of Randomized Smoothing [72.93630656906599]
  In this paper, we point out the side effects of current randomized smoothing. Specifically, we articulate and prove two major points: 1) the decision boundaries of smoothed classifiers will shrink, resulting in disparity in class-wise accuracy; 2) applying noise augmentation in the training process does not necessarily resolve the shrinking issue due to the inconsistent learning objectives.
  arXiv  Detail & Related papers  (2020-03-02T23:37:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.