Related papers: Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles

Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles

URL: http://arxiv.org/abs/2205.14116v3
Date: Thu, 21 Mar 2024 16:14:01 GMT
Title: Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles
Authors: Alexandre Forel, Axel Parmentier, Thibaut Vidal,
Abstract summary: We formalize the generation of robust counterfactual explanations as a probabilistic problem. We show the link between the robustness of ensemble models and the robustness of base learners. Our method achieves high robustness with only a small increase in the distance from counterfactual explanations to their initial observations.
Score: 50.81061839052459
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Counterfactual explanations describe how to modify a feature vector in order to flip the outcome of a trained classifier. Obtaining robust counterfactual explanations is essential to provide valid algorithmic recourse and meaningful explanations. We study the robustness of explanations of randomized ensembles, which are always subject to algorithmic uncertainty even when the training data is fixed. We formalize the generation of robust counterfactual explanations as a probabilistic problem and show the link between the robustness of ensemble models and the robustness of base learners. We develop a practical method with good empirical performance and support it with theoretical guarantees for ensembles of convex base learners. Our results show that existing methods give surprisingly low robustness: the validity of naive counterfactuals is below $50\%$ on most data sets and can fall to $20\%$ on problems with many features. In contrast, our method achieves high robustness with only a small increase in the distance from counterfactual explanations to their initial observations.

Related papers

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations [80.86128012438834]
We show for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete. We propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees.
arXiv Detail & Related papers (2024-07-10T09:13:11Z)
From Robustness to Explainability and Back Again [0.685316573653194]
The paper addresses the limitation of scalability of formal explainability, and proposes novel algorithms for computing formal explanations. The proposed algorithm computes explanations by answering instead a number of robustness queries, and such that the number of such queries is at most linear on the number of features. The experiments validate the practical efficiency of the proposed approach.
arXiv Detail & Related papers (2023-06-05T17:21:05Z)
Understanding Post-hoc Explainers: The Case of Anchors [6.681943980068051]
We present a theoretical analysis of a rule-based interpretability method that highlights a small set of words to explain a text's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results.
arXiv Detail & Related papers (2023-03-15T17:56:34Z)
Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting [80.9896041501715]
Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance. This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
arXiv Detail & Related papers (2023-02-09T18:02:34Z)
Confidence-aware Training of Smoothed Classifiers for Certified Robustness [75.95332266383417]
We use "accuracy under Gaussian noise" as an easy-to-compute proxy of adversarial robustness for an input. Our experiments show that the proposed method consistently exhibits improved certified robustness upon state-of-the-art training methods.
arXiv Detail & Related papers (2022-12-18T03:57:12Z)
Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals [72.00815192668193]
Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
arXiv Detail & Related papers (2021-06-01T20:36:48Z)
Probabilistic Sufficient Explanations [31.08715352013011]
We introduce probabilistic sufficient explanations, which formulate explaining an instance of classification as choosing the "simplest" subset of features. We design a scalable algorithm for finding the desired explanations while keeping the guarantees intact. Our experiments demonstrate the effectiveness of our algorithm in finding sufficient explanations, and showcase its advantages compared to Anchors and logical explanations.
arXiv Detail & Related papers (2021-05-21T04:03:10Z)
Low-Regret Active learning [64.36270166907788]
We develop an online learning algorithm for identifying unlabeled data points that are most informative for training. At the core of our work is an efficient algorithm for sleeping experts that is tailored to achieve low regret on predictable (easy) instances.
arXiv Detail & Related papers (2021-04-06T22:53:45Z)
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability [44.9824285459365]
Black box explanations are increasingly being employed to establish model credibility in high-stakes settings. prior work demonstrates that explanations generated by state-of-the-art techniques are inconsistent, unstable, and provide very little insight into their correctness and reliability. We develop a novel Bayesian framework for generating local explanations along with their associated uncertainty.
arXiv Detail & Related papers (2020-08-11T22:52:21Z)

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