On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples

• URL: http://arxiv.org/abs/2107.09045v1
• Date: Mon, 19 Jul 2021 17:54:10 GMT
• Title: On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples
• Authors: Verena Praher, Katharina Prinz, Arthur Flexer, Gerhard Widmer
• Abstract summary: Local explanation methods such as LIME have become popular in MIR. This paper reports on targeted investigations where we try to get more insight into the actual veracity of LIME's explanations.
• Score: 5.744593856232663
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Local explanation methods such as LIME have become popular in MIR as tools for generating post-hoc, model-agnostic explanations of a model's classification decisions. The basic idea is to identify a small set of human-understandable features of the classified example that are most influential on the classifier's prediction. These are then presented as an explanation. Evaluation of such explanations in publications often resorts to accepting what matches the expectation of a human without actually being able to verify if what the explanation shows is what really caused the model's prediction. This paper reports on targeted investigations where we try to get more insight into the actual veracity of LIME's explanations in an audio classification task. We deliberately design adversarial examples for the classifier, in a way that gives us knowledge about which parts of the input are potentially responsible for the model's (wrong) prediction. Asking LIME to explain the predictions for these adversaries permits us to study whether local explanations do indeed detect these regions of interest. We also look at whether LIME is more successful in finding perturbations that are more prominent and easily noticeable for a human. Our results suggest that LIME does not necessarily manage to identify the most relevant input features and hence it remains unclear whether explanations are useful or even misleading.

Related papers

• Evaluating the Explainability of Attributes and Prototypes for a Medical Classification Model [0.0]
  We evaluate attribute- and prototype-based explanations with the Proto-Caps model. We can conclude that attribute scores and visual prototypes enhance confidence in the model.
  arXiv  Detail & Related papers  (2024-04-15T16:43:24Z)
• Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP [7.792303263390021]
  We want to understand if machine learning models provide explanations for the classification that are reasonable to us as humans. We also want to know if the prediction quality is correlated with the quality of explanations.
  arXiv  Detail & Related papers  (2022-09-15T21:45:46Z)
• Fooling SHAP with Stealthily Biased Sampling [7.476901945542385]
  SHAP explanations aim at identifying which features contribute the most to the difference in model prediction at a specific input versus a background distribution. Recent studies have shown that they can be manipulated by malicious adversaries to produce arbitrary desired explanations. We propose a complementary family of attacks that leave the model intact and manipulate SHAP explanations using stealthily biased sampling of the data points used to approximate expectations w.r.t the background distribution.
  arXiv  Detail & Related papers  (2022-05-30T20:33:46Z)
• Visual Abductive Reasoning [85.17040703205608]
  Abductive reasoning seeks the likeliest possible explanation for partial observations. We propose a new task and dataset, Visual Abductive Reasoning ( VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations.
  arXiv  Detail & Related papers  (2022-03-26T10:17:03Z)
• Human Interpretation of Saliency-based Explanation Over Text [65.29015910991261]
  We study saliency-based explanations over textual data. We find that people often mis-interpret the explanations. We propose a method to adjust saliencies based on model estimates of over- and under-perception.
  arXiv  Detail & Related papers  (2022-01-27T15:20:32Z)
• Deconfounding to Explanation Evaluation in Graph Neural Networks [136.73451468551656]
  We argue that a distribution shift exists between the full graph and the subgraph, causing the out-of-distribution problem. We propose Deconfounded Subgraph Evaluation (DSE) which assesses the causal effect of an explanatory subgraph on the model prediction.
  arXiv  Detail & Related papers  (2022-01-21T18:05:00Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End [17.226134854746267]
  We present a method to generate feature attribution explanations from a set of counterfactual examples. We show how counterfactual examples can be used to evaluate the goodness of an attribution-based explanation in terms of its necessity and sufficiency.
  arXiv  Detail & Related papers  (2020-11-10T05:41:43Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)
• Evaluations and Methods for Explanation through Robustness Analysis [117.7235152610957]
  We establish a novel set of evaluation criteria for such feature based explanations by analysis. We obtain new explanations that are loosely necessary and sufficient for a prediction. We extend the explanation to extract the set of features that would move the current prediction to a target class.
  arXiv  Detail & Related papers  (2020-05-31T05:52:05Z)

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.