1 code implementation • 19 Dec 2023 • Yacine Izza, Kuldeep S. Meel, Joao Marques-Silva
Formal abductive explanations offer crucial guarantees of rigor and so are of interest in high-stakes uses of machine learning (ML).
no code implementations • 18 Dec 2023 • Yacine Izza, Joao Marques-Silva
The importance of ML model robustness is illustrated for example by the existence of competitions evaluating the progress of robustness tools, namely in the case of neural networks (NNs) but also by efforts towards robustness certification.
no code implementations • 30 Sep 2023 • Xuanxiang Huang, Joao Marques-Silva
Recent work demonstrated the inadequacy of Shapley values for explainable artificial intelligence (XAI).
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 6 Sep 2023 • Xuanxiang Huang, Joao Marques-Silva
This earlier work devised a brute-force approach to identify Boolean functions, defined on small numbers of features, and also associated instances, which displayed such inadequacy-revealing issues, and so served as evidence to the inadequacy of Shapley values for rule-based explainability.
1 code implementation • 27 Jun 2023 • Yacine Izza, Alexey Ignatiev, Peter Stuckey, Joao Marques-Silva
Given a set of feature values for an instance to be explained, and a resulting decision, a formal abductive explanation is a set of features, such that if they take the given value will always lead to the same decision.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 27 Jun 2023 • Ramón Béjar, António Morgado, Jordi Planes, Joao Marques-Silva
The paper shows that most of the algorithms proposed in recent years for computing logic-based explanations can be generalized for computing explanations given the partially specified inputs.
no code implementations • 27 Jun 2023 • Joao Marques-Silva, Xuanxiang Huang
Explainable artificial intelligence (XAI) aims to help human decision-makers in understanding complex machine learning (ML) models.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
no code implementations • 5 Jun 2023 • Xuanxiang Huang, Joao Marques-Silva
In contrast with ad-hoc methods for eXplainable Artificial Intelligence (XAI), formal explainability offers important guarantees of rigor.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 13 May 2023 • Joao Marques-Silva
The advances in Machine Learning (ML) in recent years have been both impressive and far-reaching.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
no code implementations • 16 Feb 2023 • 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 importance of features for predictions.
no code implementations • 12 Dec 2022 • Yacine Izza, Xuanxiang Huang, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva
One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness.
1 code implementation • 27 Oct 2022 • Xuanxiang Huang, Martin C. Cooper, Antonio Morgado, Jordi Planes, Joao Marques-Silva
Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction.
no code implementations • 24 Oct 2022 • Joao Marques-Silva
Most of these efforts have focused on so-called model-agnostic approaches.
no code implementations • 11 Jul 2022 • Yacine Izza, Joao Marques-Silva
Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations.
1 code implementation • 20 Jun 2022 • Jinqiang Yu, Alexey Ignatiev, Peter J. Stuckey, Nina Narodytska, Joao Marques-Silva
It also means the "why not" explanations may be suspect as the counterexamples they rely on may not be meaningful.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 20 May 2022 • Yacine Izza, Alexey Ignatiev, Joao Marques-Silva
The belief in DT interpretability is justified by the fact that explanations for DT predictions are generally expected to be succinct.
1 code implementation • 19 May 2022 • Yacine Izza, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva
The paper proposes two logic encodings for computing smallest {\delta}-relevant sets for DTs.
no code implementations • 15 Feb 2022 • Xuanxiang Huang, Joao Marques-Silva
In contrast, this paper shows that for a number of families of classifiers, FMP is in NP.
no code implementations • 4 Jul 2021 • Xuanxiang Huang, Yacine Izza, Alexey Ignatiev, Martin C. Cooper, Nicholas Asher, Joao Marques-Silva
Knowledge compilation (KC) languages find a growing number of practical uses, including in Constraint Programming (CP) and in Machine Learning (ML).
1 code implementation • 2 Jun 2021 • Xuanxiang Huang, Yacine Izza, Alexey Ignatiev, Joao Marques-Silva
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.
no code implementations • 1 Jun 2021 • Joao Marques-Silva, Thomas Gerspacher, Martin Cooper, Alexey Ignatiev, Nina Narodytska
This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier.
no code implementations • 1 Jun 2021 • Yacine Izza, Alexey Ignatiev, Nina Narodytska, Martin C. Cooper, Joao Marques-Silva
Recent work proposed $\delta$-relevant inputs (or sets) as a probabilistic explanation for the predictions made by a classifier on a given input.
no code implementations • 21 May 2021 • Yacine Izza, Joao Marques-Silva
Random Forest (RFs) are among the most widely used Machine Learning (ML) classifiers.
no code implementations • 14 May 2021 • Alexey Ignatiev, Joao Marques-Silva
Unfortunately, and in clear contrast with the case of DTs, this paper shows that computing explanations for DLs is computationally hard.
no code implementations • 18 Mar 2021 • Takfarinas Saber, Anthony Ventresque, Joao Marques-Silva, James Thorburn, Liam Murphy
Machine Reassignment is a challenging problem for constraint programming (CP) and mixed-integer linear programming (MILP) approaches, especially given the size of data centres.
1 code implementation • 3 Feb 2021 • Alexey Ignatiev, Edward Lam, Peter J. Stuckey, Joao Marques-Silva
Machine learning (ML) is ubiquitous in modern life.
no code implementations • 1 Jan 2021 • Aditya Aniruddha Shrotri, Nina Narodytska, Alexey Ignatiev, Joao Marques-Silva, Kuldeep S. Meel, Moshe Vardi
Modern machine learning techniques have enjoyed widespread success, but are plagued by lack of transparency in their decision making, which has led to the emergence of the field of explainable AI.
no code implementations • 1 Jan 2021 • Alexey Ignatiev, Nina Narodytska, Nicholas Asher, Joao Marques-Silva
Explanations of Machine Learning (ML) models often address a ‘Why?’ question.
no code implementations • 21 Dec 2020 • Alexey Ignatiev, Nina Narodytska, Nicholas Asher, Joao Marques-Silva
and 'Why Not?'
no code implementations • 21 Oct 2020 • Yacine Izza, Alexey Ignatiev, Joao Marques-Silva
Decision trees (DTs) epitomize what have become to be known as interpretable machine learning (ML) models.
no code implementations • NeurIPS 2020 • Joao Marques-Silva, Thomas Gerspacher, Martin C. Cooper, Alexey Ignatiev, Nina Narodytska
In contrast, we show that the computation of one PI-explanation for an NBC can be achieved in log-linear time, and that the same result also applies to the more general class of linear classifiers.
1 code implementation • NeurIPS 2019 • Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva
The importance of explanations (XP's) of machine learning (ML) model predictions and of adversarial examples (AE's) cannot be overstated, with both arguably being essential for the practical success of ML in different settings.
1 code implementation • 4 Jul 2019 • Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva
Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions.
1 code implementation • 26 Nov 2018 • Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva
The experimental results, obtained on well-known datasets, validate the scalability of the proposed approach as well as the quality of the computed solutions.
no code implementations • 27 Apr 2016 • Alexey Ignatiev, Antonio Morgado, Joao Marques-Silva
Propositional abduction is a restriction of abduction to the propositional domain, and complexity-wise is in the second level of the polynomial hierarchy.
no code implementations • 8 Oct 2013 • Anton Belov, Antonio Morgado, Joao Marques-Silva
The key requirement in this setting is that the preprocessing has to be sound, i. e. so that the solution can be reconstructed correctly and efficiently after the execution of a MaxSAT algorithm on the preprocessed instance.