Evaluating counterfactual explanations using Pearl's counterfactual method

• URL: http://arxiv.org/abs/2301.02499v1
• Date: Fri, 6 Jan 2023 13:18:26 GMT
• Title: Evaluating counterfactual explanations using Pearl's counterfactual method
• Authors: Bevan I. Smith
• Abstract summary: Counterfactual explanations (CEs) are methods for generating an alternative scenario that produces a different desirable outcome. CEs are currently generated from machine learning models that do not necessarily take into account the true causal structure in the data. I propose in this study to test the CEs using Judea Pearl's method of computing counterfactuals.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counterfactual explanations (CEs) are methods for generating an alternative scenario that produces a different desirable outcome. For example, if a student is predicted to fail a course, then counterfactual explanations can provide the student with alternate ways so that they would be predicted to pass. The applications are many. However, CEs are currently generated from machine learning models that do not necessarily take into account the true causal structure in the data. By doing this, bias can be introduced into the CE quantities. I propose in this study to test the CEs using Judea Pearl's method of computing counterfactuals which has thus far, surprisingly, not been seen in the counterfactual explanation (CE) literature. I furthermore evaluate these CEs on three different causal structures to show how the true underlying causal structure affects the CEs that are generated. This study presented a method of evaluating CEs using Pearl's method and it showed, (although using a limited sample size), that thirty percent of the CEs conflicted with those computed by Pearl's method. This shows that we cannot simply trust CEs and it is vital for us to know the true causal structure before we blindly compute counterfactuals using the original machine learning model.

Related papers

• Counterfactual Explanations for Linear Optimization [0.0]
  The concept of counterfactual explanations (CE) has emerged as one of the important concepts to understand the inner workings of complex AI systems. In this paper, we translate the idea of CEs to linear optimization and propose, motivate, and analyze three different types of CEs: strong, weak, and relative.
  arXiv  Detail & Related papers  (2024-05-24T10:58:00Z)
• Introducing User Feedback-based Counterfactual Explanations (UFCE) [49.1574468325115]
  Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in XAI. UFCE allows for the inclusion of user constraints to determine the smallest modifications in the subset of actionable features. UFCE outperforms two well-known CE methods in terms of textitproximity, textitsparsity, and textitfeasibility.
  arXiv  Detail & Related papers  (2024-02-26T20:09:44Z)
• Counterfactual Explanation for Regression via Disentanglement in Latent Space [19.312306559210125]
  We introduce a novel method to generate Counterfactual Explanations (CEs) for a pre-trained regressor. We show that our method maintains the characteristics of the query sample during the counterfactual search. Our code will be made available as an open-source package upon the publication of this work.
  arXiv  Detail & Related papers  (2023-11-14T15:08:14Z)
• Learning to Scaffold: Optimizing Model Explanations for Teaching [74.25464914078826]
  We train models on three natural language processing and computer vision tasks. We find that students trained with explanations extracted with our framework are able to simulate the teacher significantly more effectively than ones produced with previous methods.
  arXiv  Detail & Related papers  (2022-04-22T16:43:39Z)
• On the Robustness of Counterfactual Explanations to Adverse Perturbations [0.0]
  We consider robustness to adverse perturbations, which may naturally happen due to unfortunate circumstances. We provide two definitions of robustness, which concern, respectively, the features to change and to keep as they are. Our experiments show that CEs are often not robust and, if adverse perturbations take place, the intervention they prescribe may require a much larger cost than anticipated.
  arXiv  Detail & Related papers  (2022-01-22T13:57:45Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)
• Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect [95.37587481952487]
  Long-tailed classification is the key to deep learning at scale. Existing methods are mainly based on re-weighting/resamplings that lack a fundamental theory. In this paper, we establish a causal inference framework, which not only unravels the whys of previous methods, but also derives a new principled solution.
  arXiv  Detail & Related papers  (2020-09-28T00:32:11Z)
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples [0.0]
  We argue that the relationship to the true label and the tolerance with respect to proximity are two properties that formally distinguish CEs and AEs. We show connections between current methods for generating CEs and AEs, and estimate that the fields will merge more and more as the number of common use-cases grows.
  arXiv  Detail & Related papers  (2020-09-11T15:09:12Z)
• On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning [15.965337956587373]
  PlausIble Exceptionality-based Contrastive Explanations (PIECE), modifies all exceptional features in a test image to be normal from the perspective of the counterfactual class. Two controlled experiments compare PIECE to others in the literature, showing that PIECE not only generates the most plausible counterfactuals on several measures, but also the best semifactuals.
  arXiv  Detail & Related papers  (2020-09-10T14:48:12Z)
• SCOUT: Self-aware Discriminant Counterfactual Explanations [78.79534272979305]
  The problem of counterfactual visual explanations is considered. A new family of discriminant explanations is introduced. The resulting counterfactual explanations are optimization free and thus much faster than previous methods.
  arXiv  Detail & Related papers  (2020-04-16T17:05:49Z)

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.