Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks30 from public data
- On Explaining Random Forests with SAT104
This paper proves that computing one PI-explanation of an RF is D^P-hard, and proposes a propositional encoding for computing explanations of RFs, thus enabling finding PI-Explanations with a SAT solver.
- Using MaxSAT for Efficient Explanations of Tree Ensembles85
Experimental results obtained demonstrate that the proposed MaxSAT-based approach is either on par or outperforms the existing reasoning-based explainers, thus representing a robust and efficient alternative for computing formal explanations for TEs.
- On Tackling Explanation Redundancy in Decision Trees85
This paper offers both theoretical and experimental arguments demonstrating that, as long as interpretability of decision trees equates with succinctness of explanations, then decision trees ought not be deemed interpretable.
- On Efficiently Explaining Graph-Based Classifiers57
The paper shows that the set of all contrastive explanations can be enumerated in polynomial time, and proposes a practically efficient solution for the enumeration of explanations, and studies the complexity of deciding whether a given feature is included in some explanation.
- Tractable Explanations for d-DNNF Classifiers46
This paper shows that for classifiers represented with some of the best-known propositional languages, different kinds of explanations can be computed in polynomial time, for any propositional language that is strictly less succinct than d-DNNF.
- Boosting MCSes Enumeration30
In the paper, a technique is introduced that boosts the currently most efficient practical approaches to enumerate MCSes and implements a model rotation paradigm that allows the set of M CSes to be computed in an heuristically efficient way.
- Delivering Inflated Explanations24
This paper formally defines inflated explanations, which is a set of features, and for each feature a set of values, such that the decision will remain unchanged, for any of the values allowed for any of the features in the (inflated) abductive explanation.
- Solving Explainability Queries with Quantification: The Case of Feature Relevancy17
This paper proposes a novel algorithm for the feature relevancy problem (FRP) which is applicable to any ML classifier that meets minor requirements, and shows that the novel algorithm is efficient in practice.
- 17
- Most General Explanations of Tree Ensembles (Extended Version)11
This paper shows how to find a most general abductive explanation for an AI decision that covers as much of the input space as possible, while still being a correct formal explanation of the model's behaviour.
- Provably Precise, Succinct and Efficient Explanations for Decision Trees10
Two logic encodings for computing smallest {\delta}-relevant sets for DTs are proposed and a polynomial-time algorithm is devised which is not guaranteed to be subset-minimal, but for which the experiments show to be most often subset-Minimal in practice.
- 9
- On the Enumeration of Association Rules: A Decomposition-based Approach9
This paper introduces a practical SAT-based approach to discover efficiently (minimal non-redundant) association rules by presenting a decomposition-based paradigm that splits the original transaction database into smaller and independent subsets.
- 7
- On Computing Relevant Features for Explaining NBCs6
This paper investigates the computation of relevant sets for Naive Bayes Classifiers (NBCs) and shows that, in practice, these are easy to compute, and confirms that succinct sets of relevant features can be obtained with NBCs.
- 5
- 5
- 5
- 4
- On the Extraction of One Maximal Information Subset That Does Not Conflict with Multiple Contexts4
This paper addresses the efficient extraction of one maximal information subset that does not conflict with multiple contxts or additional information sources from a computational point of view in clausal Boolean logic.
- Repairing LLM Executions for Secure Automatic Programming3
Critical insights are revealed into why LLMs produce code vulnerabilities: they explicitly learn vulnerability patterns and actively use them during inference, and it is demonstrated how this can be leveraged to repair LLM executions, allowing us to avoid such vulnerability patterns.
- 3
- Efficient Contrastive Explanations on Demand2
This paper proposes novel algorithms to compute the so-called contrastive explanations for ML models with a large number of features, by leveraging on adversarial robustness, by leveraging on adversarial robustness.
- Rigorous Explanations for Tree Ensembles1
This paper investigates the computation of rigorously-defined, logically-sound explanations for the concrete case of two well-known examples of tree ensembles, namely random forests and boosted trees.
- On Tackling Explanation Redundancy in Decision Trees (Extended Abstract)1
This paper overviews recent theoretical and practical results which demonstrate that for most decision trees, tree paths exhibit so-called explanation redundancy, in that logically sound explanations can often be significantly more succinct than what the features in the path dictates.
- An Ontology-based Approach for Building and Querying ICH Video Datasets1
This work proposes a completion of the ontology for Vietnamese ICH by semantically enriching traditional dance videos through manual annotation, and addresses inconsistencies which emerge when the same video receives conflicting annotations from multiple sources.
- On Admissible Consensuses1
It is shown that a family of consensuses might not actually be endorsed by open-minded agents, due to the usual ad-hoc logical representation of knowledge and well-known paradoxes linked to material implication.
- 1
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.