Search Results for author:
Found 36 papers, 10 papers with code
Locally-Minimal Probabilistic Explanations
Formal abductive explanations offer crucial guarantees of rigor and so are of interest in high-stakes uses of machine learning (ML).
The Pros and Cons of Adversarial Robustness
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.
Refutation of Shapley Values for XAI -- Additional Evidence
Recent work demonstrated the inadequacy of Shapley values for explainable artificial intelligence (XAI).
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
A Refutation of Shapley Values for Explainability
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.
Delivering Inflated Explanations
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)
On Logic-Based Explainability with Partially Specified Inputs
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.
Explainability is NOT a Game
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
From Robustness to Explainability and Back Again
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)
Disproving XAI Myths with Formal Methods -- Initial Results
The advances in Machine Learning (ML) in recent years have been both impressive and far-reaching.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
The Inadequacy of Shapley Values for Explainability
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.
On Computing Probabilistic Abductive Explanations
One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness.
Feature Necessity & Relevancy in ML Classifier Explanations
Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction.
Logic-Based Explainability in Machine Learning
Most of these efforts have focused on so-called model-agnostic approaches.
On Computing Relevant Features for Explaining NBCs
Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations.
Eliminating The Impossible, Whatever Remains Must Be True
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)
On Tackling Explanation Redundancy in Decision Trees
The belief in DT interpretability is justified by the fact that explanations for DT predictions are generally expected to be succinct.
Provably Precise, Succinct and Efficient Explanations for Decision Trees
The paper proposes two logic encodings for computing smallest {\delta}-relevant sets for DTs.
On Deciding Feature Membership in Explanations of SDD & Related Classifiers
In contrast, this paper shows that for a number of families of classifiers, FMP is in NP.
Efficient Explanations for Knowledge Compilation Languages
Knowledge compilation (KC) languages find a growing number of practical uses, including in Constraint Programming (CP) and in Machine Learning (ML).
On Efficiently Explaining Graph-Based Classifiers
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.
Explanations for Monotonic Classifiers
This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier.
Efficient Explanations With Relevant Sets
Recent work proposed $\delta$-relevant inputs (or sets) as a probabilistic explanation for the predictions made by a classifier on a given input.
On Explaining Random Forests with SAT
Random Forest (RFs) are among the most widely used Machine Learning (ML) classifiers.
SAT-Based Rigorous Explanations for Decision Lists
Unfortunately, and in clear contrast with the case of DTs, this paper shows that computing explanations for DLs is computationally hard.
MILP for the Multi-objective VM Reassignment Problem
Machine Reassignment is a challenging problem for constraint programming (CP) and mixed-integer linear programming (MILP) approaches, especially given the size of data centres.
A Scalable Two Stage Approach to Computing Optimal Decision Sets
Machine learning (ML) is ubiquitous in modern life.
Constraint-Driven Explanations of Black-Box ML Models
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.
On Relating "Why?" and "Why Not?" Explanations
Explanations of Machine Learning (ML) models often address a ‘Why?’ question.
On Explaining Decision Trees
Decision trees (DTs) epitomize what have become to be known as interpretable machine learning (ML) models.
Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay
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.
On Relating Explanations and Adversarial Examples
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.
On Validating, Repairing and Refining Heuristic ML Explanations
Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions.
Abduction-Based Explanations for Machine Learning Models
The experimental results, obtained on well-known datasets, validate the scalability of the proposed approach as well as the quality of the computed solutions.
Propositional Abduction with Implicit Hitting Sets
Propositional abduction is a restriction of abduction to the propositional domain, and complexity-wise is in the second level of the polynomial hierarchy.
SAT-based Preprocessing for MaxSAT (extended version)
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.
