How Reliable and Stable are Explanations of XAI Methods?

• URL: http://arxiv.org/abs/2407.03108v1
• Date: Wed, 3 Jul 2024 13:47:41 GMT
• Title: How Reliable and Stable are Explanations of XAI Methods?
• Authors: José Ribeiro, Lucas Cardoso, Vitor Santos, Eduardo Carvalho, Níkolas Carneiro, Ronnie Alves,
• Abstract summary: Black box models are increasingly being used in the daily lives of human beings living in society. There has been the emergence of Explainable Artificial Intelligence (XAI) methods aimed at generating additional explanations regarding how the model makes certain predictions. It was found that current XAI methods are sensitive to perturbations, with the exception of one specific method.
• Score: 0.4749981032986242
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Black box models are increasingly being used in the daily lives of human beings living in society. Along with this increase, there has been the emergence of Explainable Artificial Intelligence (XAI) methods aimed at generating additional explanations regarding how the model makes certain predictions. In this sense, methods such as Dalex, Eli5, eXirt, Lofo and Shap emerged as different proposals and methodologies for generating explanations of black box models in an agnostic way. Along with the emergence of these methods, questions arise such as "How Reliable and Stable are XAI Methods?". With the aim of shedding light on this main question, this research creates a pipeline that performs experiments using the diabetes dataset and four different machine learning models (LGBM, MLP, DT and KNN), creating different levels of perturbations of the test data and finally generates explanations from the eXirt method regarding the confidence of the models and also feature relevances ranks from all XAI methods mentioned, in order to measure their stability in the face of perturbations. As a result, it was found that eXirt was able to identify the most reliable models among all those used. It was also found that current XAI methods are sensitive to perturbations, with the exception of one specific method.

Related papers

• Robustness of Explainable Artificial Intelligence in Industrial Process Modelling [43.388607981317016]
  We evaluate current XAI methods by scoring them based on ground truth simulations and sensitivity analysis. We show the differences between XAI methods in their ability to correctly predict the true sensitivity of the modeled industrial process.
  arXiv  Detail & Related papers  (2024-07-12T09:46:26Z)
• Unified Explanations in Machine Learning Models: A Perturbation Approach [0.0]
  Inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. We propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap) We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold.
  arXiv  Detail & Related papers  (2024-05-30T16:04:35Z)
• Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligence [15.415120542032547]
  XAI seeks to make AI systems more understandable and trustworthy. This work analyses the value of data morphology strategies in generating counterfactual explanations. It introduces the Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF) method.
  arXiv  Detail & Related papers  (2024-05-20T18:51:42Z)
• An Experimental Investigation into the Evaluation of Explainability Methods [60.54170260771932]
  This work compares 14 different metrics when applied to nine state-of-the-art XAI methods and three dummy methods (e.g., random saliency maps) used as references. Experimental results show which of these metrics produces highly correlated results, indicating potential redundancy.
  arXiv  Detail & Related papers  (2023-05-25T08:07:07Z)
• Topological Interpretability for Deep-Learning [0.30806551485143496]
  Deep learning (DL) models cannot quantify the certainty of their predictions. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text.
  arXiv  Detail & Related papers  (2023-05-15T13:38:13Z)
• A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME [4.328967621024592]
  We propose a framework for interpretation of two widely used XAI methods. We discuss their outcomes in terms of model-dependency and in the presence of collinearity. The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation.
  arXiv  Detail & Related papers  (2023-05-03T10:04:46Z)
• Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement [75.00655434905417]
  Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically for improving various properties of ML models. We show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning.
  arXiv  Detail & Related papers  (2022-03-15T15:44:28Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)
• Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? [97.77183117452235]
  We carry out human subject tests to isolate the effect of algorithmic explanations on model interpretability. Clear evidence of method effectiveness is found in very few cases. Our results provide the first reliable and comprehensive estimates of how explanations influence simulatability.
  arXiv  Detail & Related papers  (2020-05-04T20:35:17Z)

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.