12 citations · 51 across the 21 of their papers we have counts for
21 papers
Towards Rigorous Explainability by Feature Attribution
Olivier Létoffé, Xuanxiang Huang, Joao Marques-Silva
For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models. Unfortunately, such methods lack rigor and can mislea…
A Parallel Approach to Counting Exact Covers Based on Decomposability Property
Liangda Fang, Yaohui Luo, Delong Li +2
The exact cover problem is a classical NP-hard problem with broad applications in the area of AI. Algorithm DXZ is a method to count exact covers representing by zero-suppressed bi…
Rigorous Explanations for Tree Ensembles
Yacine Izza, Alexey Ignatiev, Xuanxiang Huang +2
Tree ensembles (TEs) find a multitude of practical applications. They represent one of the most general and accurate classes of machine learning methods. While they are typically q…
Unifying Formal Explanations: A Complexity-Theoretic Perspective
Shahaf Bassan, Xuanxiang Huang, Guy Katz
Previous work has explored the computational complexity of deriving two fundamental types of explanations for ML model predictions: (1) *sufficient reasons*, which are subsets of i…
Uncovering Bugs in Formal Explainers: A Case Study with PyXAI
Xuanxiang Huang, Yacine Izza, Alexey Ignatiev +1
Formal explainable artificial intelligence (XAI) offers unique theoretical guarantees of rigor when compared to other non-formal methods of explainability. However, little attentio…
Rigorous Feature Importance Scores based on Shapley Value and Banzhaf Index
Xuanxiang Huang, Olivier Létoffé, Joao Marques-Silva
Feature attribution methods based on game theory are ubiquitous in the field of eXplainable Artificial Intelligence (XAI). Recent works proposed rigorous feature attribution using…
The Explanation Game -- Rekindled (Extended Version)
Joao Marques-Silva, Xuanxiang Huang, Olivier Letoffe
Recent work demonstrated the existence of critical flaws in the current use of Shapley values in explainable AI (XAI), i.e. the so-called SHAP scores. These flaws are significant i…
SHAP scores fail pervasively even when Lipschitz succeeds
Olivier Letoffe, Xuanxiang Huang, Joao Marques-Silva
The ubiquitous use of Shapley values in eXplainable AI (XAI) has been triggered by the tool SHAP, and as a result are commonly referred to as SHAP scores. Recent work devised examp…
From SHAP Scores to Feature Importance Scores
Olivier Letoffe, Xuanxiang Huang, Nicholas Asher +1
A central goal of eXplainable Artificial Intelligence (XAI) is to assign relative importance to the features of a Machine Learning (ML) model given some prediction. The importance…
Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementation
Yacine Izza, Xuanxiang Huang, Antonio Morgado +3
The uses of machine learning (ML) have snowballed in recent years. In many cases, ML models are highly complex, and their operation is beyond the understanding of human decision-ma…
Towards trustable SHAP scores
Olivier Letoffe, Xuanxiang Huang, Joao Marques-Silva
SHAP scores represent the proposed use of the well-known Shapley values in eXplainable Artificial Intelligence (XAI). Recent work has shown that the exact computation of SHAP score…
Refutation of Shapley Values for XAI -- Additional Evidence
Xuanxiang Huang, Joao Marques-Silva
Recent work demonstrated the inadequacy of Shapley values for explainable artificial intelligence (XAI). Although to disprove a theory a single counterexample suffices, a possible…
A Refutation of Shapley Values for Explainability
Xuanxiang Huang, Joao Marques-Silva
Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanat…
Explainability is NOT a Game
Joao Marques-Silva, Xuanxiang Huang
Explainable artificial intelligence (XAI) aims to help human decision-makers in understanding complex machine learning (ML) models. One of the hallmarks of XAI are measures of rela…
From Robustness to Explainability and Back Again
Xuanxiang Huang, Joao Marques-Silva
Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, sin…
The Inadequacy of Shapley Values for Explainability
Xuanxiang Huang, Joao Marques-Silva
This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importan…
On Computing Probabilistic Abductive Explanations
Yacine Izza, Xuanxiang Huang, Alexey Ignatiev +3
The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches…
Feature Necessity & Relevancy in ML Classifier Explanations
Xuanxiang Huang, Martin C. Cooper, Antonio Morgado +2
Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. In some applications, and besides ask…
On Deciding Feature Membership in Explanations of SDD & Related Classifiers
Xuanxiang Huang, Joao Marques-Silva
When reasoning about explanations of Machine Learning (ML) classifiers, a pertinent query is to decide whether some sensitive features can serve for explaining a given prediction.…
Efficient Explanations for Knowledge Compilation Languages
Xuanxiang Huang, Yacine Izza, Alexey Ignatiev +3
Knowledge compilation (KC) languages find a growing number of practical uses, including in Constraint Programming (CP) and in Machine Learning (ML). In most applications, one natur…
On Efficiently Explaining Graph-Based Classifiers
Xuanxiang Huang, Yacine Izza, Alexey Ignatiev +1
Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper…