Related papers: Axiomatic Characterisations of Sample-based Explainers

Axiomatic Characterisations of Sample-based Explainers

URL: http://arxiv.org/abs/2408.04903v2
Date: Mon, 12 Aug 2024 07:04:56 GMT
Title: Axiomatic Characterisations of Sample-based Explainers
Authors: Leila Amgoud, Martin C. Cooper, Salim Debbaoui,
Abstract summary: We scrutinize explainers that generate feature-based explanations from samples or datasets. We identify the entire family of explainers that satisfy two key properties which are compatible with all the others. We introduce the first (broad family of) explainers that guarantee the existence of explanations and irrefutable global consistency.
Score: 8.397730500554047
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Explaining decisions of black-box classifiers is both important and computationally challenging. In this paper, we scrutinize explainers that generate feature-based explanations from samples or datasets. We start by presenting a set of desirable properties that explainers would ideally satisfy, delve into their relationships, and highlight incompatibilities of some of them. We identify the entire family of explainers that satisfy two key properties which are compatible with all the others. Its instances provide sufficient reasons, called weak abductive explanations.We then unravel its various subfamilies that satisfy subsets of compatible properties. Indeed, we fully characterize all the explainers that satisfy any subset of compatible properties. In particular, we introduce the first (broad family of) explainers that guarantee the existence of explanations and their global consistency.We discuss some of its instances including the irrefutable explainer and the surrogate explainer whose explanations can be found in polynomial time.

Related papers

Abductive explanations of classifiers under constraints: Complexity and properties [6.629765271909503]
We propose three new types of explanations that take into account constraints. They can be generated from the whole feature space or from a dataset. We show that coverage is powerful enough to discard redundant and superfluous AXp's.
arXiv Detail & Related papers (2024-09-18T17:15:39Z)
Axiomatic Aggregations of Abductive Explanations [13.277544022717404]
Recent criticisms of robustness of post hoc model approximation explanation methods have led to rise of model-precise abductive explanations. In such cases, providing a single abductive explanation can be insufficient; on the other hand, providing all valid abductive explanations can be incomprehensible due to their size. We propose three aggregation methods: two based on power indices from cooperative game theory and a third based on a well-known measure of causal strength.
arXiv Detail & Related papers (2023-09-29T04:06:10Z)
Ensemble of Counterfactual Explainers [17.88531216690148]
We propose an ensemble of counterfactual explainers that boosts weak explainers, which provide only a subset of such properties. The ensemble runs weak explainers on a sample of instances and of features, and it combines their results by exploiting a diversity-driven selection function.
arXiv Detail & Related papers (2023-08-29T10:21:50Z)
A New Class of Explanations for Classifiers with Non-Binary Features [11.358487655918676]
Two types of explanations have been receiving increased attention in the literature when analyzing the decisions made by classifiers. We show that these explanations can be significantly improved in the presence of non-binary features. Necessary and sufficient reasons were also shown to be the prime implicates and implicants of the complete reason for a decision.
arXiv Detail & Related papers (2023-04-28T11:05:46Z)
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)
Complementary Explanations for Effective In-Context Learning [77.83124315634386]
Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts. This work aims to better understand the mechanisms by which explanations are used for in-context learning.
arXiv Detail & Related papers (2022-11-25T04:40:47Z)
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)
Contrastive Explanations for Model Interpretability [77.92370750072831]
We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
arXiv Detail & Related papers (2021-03-02T00:36:45Z)
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)
A Formal Approach to Explainability [100.12889473240237]
We study the links between explanation-generating functions and intermediate representations of learned models. We study the intersection and union of explanations as a way to construct new explanations.
arXiv Detail & Related papers (2020-01-15T10:06:47Z)

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