Revisiting the robustness of post-hoc interpretability methods

• URL: http://arxiv.org/abs/2407.19683v1
• Date: Mon, 29 Jul 2024 03:55:52 GMT
• Title: Revisiting the robustness of post-hoc interpretability methods
• Authors: Jiawen Wei, Hugues Turbé, Gianmarco Mengaldo,
• Abstract summary: Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI) Different post-hoc interpretability methods often provide different results, casting doubts on their accuracy. We propose an approach and two new metrics to provide a fine-grained assessment of post-hoc interpretability methods.
• Score: 1.5020330976600738
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed important to make a decision. However, different post-hoc interpretability methods often provide different results, casting doubts on their accuracy. For this reason, several evaluation strategies have been proposed to understand the accuracy of post-hoc interpretability. Many of these evaluation strategies provide a coarse-grained assessment -- i.e., they evaluate how the performance of the model degrades on average by corrupting different data points across multiple samples. While these strategies are effective in selecting the post-hoc interpretability method that is most reliable on average, they fail to provide a sample-level, also referred to as fine-grained, assessment. In other words, they do not measure the robustness of post-hoc interpretability methods. We propose an approach and two new metrics to provide a fine-grained assessment of post-hoc interpretability methods. We show that the robustness is generally linked to its coarse-grained performance.

Related papers

• A practical approach to evaluating the adversarial distance for machine learning classifiers [2.2120851074630177]
  This paper investigates the estimation of the more informative adversarial distance using iterative adversarial attacks and a certification approach. We find that our adversarial attack approach is effective compared to related implementations, while the certification method falls short of expectations.
  arXiv  Detail & Related papers  (2024-09-05T14:57:01Z)
• BEExAI: Benchmark to Evaluate Explainable AI [0.9176056742068812]
  We propose BEExAI, a benchmark tool that allows large-scale comparison of different post-hoc XAI methods. We argue that the need for a reliable way of measuring the quality and correctness of explanations is becoming critical.
  arXiv  Detail & Related papers  (2024-07-29T11:21:17Z)
• 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)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus [10.135749005469686]
  One of the unsolved challenges in the field of Explainable AI (XAI) is determining how to most reliably estimate the quality of an explanation method. We address this issue through a meta-evaluation of different quality estimators in XAI. Our novel framework, MetaQuantus, analyses two complementary performance characteristics of a quality estimator.
  arXiv  Detail & Related papers  (2023-02-14T18:59:02Z)
• On The Coherence of Quantitative Evaluation of Visual Explanations [0.7212939068975619]
  Evaluation methods have been proposed to assess the "goodness" of visual explanations. We study a subset of the ImageNet-1k validation set where we evaluate a number of different commonly-used explanation methods. Results of our study suggest that there is a lack of coherency on the grading provided by some of the considered evaluation methods.
  arXiv  Detail & Related papers  (2023-02-14T13:41:57Z)
• SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability [11.230696151134367]
  Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. It is vital to assess how robust DL interpretability is, given an XAI method.
  arXiv  Detail & Related papers  (2022-08-19T16:07:22Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions [51.8695223602729]
  adversarial attack methods have been developed to challenge the robustness of machine learning models. We propose a Piece-wise Sampling Curving (PSC) toolkit to effectively address the discrepancy. PSC toolkit offers options for balancing the computational cost and evaluation effectiveness.
  arXiv  Detail & Related papers  (2021-04-22T14:36:51Z)
• A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods [60.04142561088524]
  We find that the confidence intervals are rather wide, demonstrating high uncertainty in how reliable automatic metrics truly are. Although many metrics fail to show statistical improvements over ROUGE, two recent works, QAEval and BERTScore, do in some evaluation settings.
  arXiv  Detail & Related papers  (2021-03-31T18:28:14Z)
• Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
  We present a general methodology for interpretable evaluation for the named entity recognition (NER) task. The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them. By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
  arXiv  Detail & Related papers  (2020-11-13T10:53:27Z)

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.