Sufficient Reasons for Classifier Decisions in the Presence of Domain Constraints

Gorji, Niku; Rubin, Sasha

doi:10.1609/aaai.v36i5.20507

Cited by 19 publications

(29 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One additional solution for computing an AXp is to formulate the problem as finding a minimal correction subset (MCS) of a propositional Horn formula, and then exploiting existing efficient algorithms (Arif et al, 2015;Marques-Silva et al, 2016). Besides enabling efficient implementations, the Horn encoding allows for integrating constraints that restrict the feature space by disallowing points in feature space that violate those constraints (Gorji and Rubin, 2021). As long as the added constraints are also Horn, and this is the case with propositional rules, then the complexity of reasoning is unaffected.…”

Section: Abductive Path Explanations By Propositional Horn Encodingmentioning

confidence: 99%

“…9. A sample of references on formal explainability includes(Shih et al, 2018;Ignatiev et al, 2019a;Shih et al, 2019;Ignatiev et al, 2019b;Narodytska et al, 2019;Wolf et al, 2019;Audemard et al, 2020;Darwiche, 2020;Darwiche and Hirth, 2020;Shi et al, 2020;Rago et al, 2020;Boumazouza et al, 2020;Ignatiev et al, 2020b;Izza et al, 2020;Marques-Silva et al, 2021;Malfa et al, 2021;Huang et al, 2021b;Audemard et al, 2021;Asher et al, 2021;Cooper and Marques-Silva, 2021;Boumazouza et al, 2021;Huang et al, 2021a;Rago et al, 2021;Liu and Lorini, 2021;Wäldchen et al, 2021;Darwiche and Marquis, 2021;Blanc et al, 2021;Arenas et al, 2021;Huang et al, 2022;Ignatiev et al, 2022;Marques-Silva and Ignatiev, 2022;Gorji and Rubin, 2022). 10.…”

unclassified

See 1 more Smart Citation

On Tackling Explanation Redundancy in Decision Trees

Izza¹,

Ignatiev²,

Marques-Silva³

2022

jair

View full text Add to dashboard Cite

Decision trees (DTs) epitomize the ideal of interpretability of machine learning (ML) models. The interpretability of decision trees motivates explainability approaches by so-called intrinsic interpretability, and it is at the core of recent proposals for applying interpretable ML models in high-risk applications. The belief in DT interpretability is justified by the fact that explanations for DT predictions are generally expected to be succinct. Indeed, in the case of DTs, explanations correspond to DT paths. Since decision trees are ideally shallow, and so paths contain far fewer features than the total number of features, explanations in DTs are expected to be succinct, and hence interpretable. 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. The paper introduces logically rigorous path explanations and path explanation redundancy, and proves that there exist functions for which decision trees must exhibit paths with explanation redundancy that is arbitrarily larger than the actual path explanation. The paper also proves that only a very restricted class of functions can be represented with DTs that exhibit no explanation redundancy. In addition, the paper includes experimental results substantiating that path explanation redundancy is observed ubiquitously in decision trees, including those obtained using different tree learning algorithms, but also in a wide range of publicly available decision trees. The paper also proposes polynomial-time algorithms for eliminating path explanation redundancy, which in practice require negligible time to compute. Thus, these algorithms serve to indirectly attain irreducible, and so succinct, explanations for decision trees. Furthermore, the paper includes novel results related with duality and enumeration of explanations, based on using SAT solvers as witness-producing NP-oracles.

show abstract

Section: Abductive Path Explanations By Propositional Horn Encodingmentioning

confidence: 99%

unclassified

On Tackling Explanation Redundancy in Decision Trees

Izza¹,

Ignatiev²,

Marques-Silva³

2022

jair

View full text Add to dashboard Cite

show abstract

“…(B) Mapping of features. Boumazouza et al, 2020Boumazouza et al, , 2021Darwiche, 2020;Darwiche andHirth, 2020, 2022;Izza et al, 2020Izza et al, , 2022a, 2021Rago et al, 2020Rago et al, , 2021Shi et al, 2020;Amgoud, 2021;Arenas et al, 2021;Asher et al, 2021;Blanc et al, 2021Blanc et al, , 2022aCooper and Marques-Silva, 2021;Darwiche and Marquis, 2021;Huang et al, 2021aHuang et al, ,b, 2022Ignatiev and Marques-Silva, 2021;Marques-Silva, 2021, 2022;Lorini, 2021, 2022a;Malfa et al, 2021;Wäldchen et al, 2021;Amgoud and Ben-Naim, 2022;Ferreira et al, 2022;Gorji and Rubin, 2022;Marques-Silva and Ignatiev, 2022;Wäldchen, 2022;Yu et al, 2022), and are characterized by formally provable guarantees of rigor, given the underlying ML models. Given such guarantees of rigor, logic-based explainability should be contrasted with well-known model-agnostic approaches to XAI (Ribeiro et al, 2016(Ribeiro et al, , 2018Lundberg and Lee, 2017;Guidotti et al, 2019), which offer no guarantees of rigor.…”

Section: Logic Foundationsmentioning

confidence: 99%

No silver bullet: interpretable ML models must be explained

Marques-Silva

Ignatiev

2023

Front. Artif. Intell.

View full text Add to dashboard Cite

Recent years witnessed a number of proposals for the use of the so-called interpretable models in specific application domains. These include high-risk, but also safety-critical domains. In contrast, other works reported some pitfalls of machine learning model interpretability, in part justified by the lack of a rigorous definition of what an interpretable model should represent. This study proposes to relate interpretability with the ability of a model to offer explanations of why a prediction is made given some point in feature space. Under this general goal of offering explanations to predictions, this study reveals additional limitations of interpretable models. Concretely, this study considers application domains where the purpose is to help human decision makers to understand why some prediction was made or why was not some other prediction made, and where irreducible (and so minimal) information is sought. In such domains, this study argues that answers to such why (or why not) questions can exhibit arbitrary redundancy, i.e., the answers can be simplified, as long as these answers are obtained by human inspection of the interpretable ML model representation.

show abstract

“…Given the above, and as long as the allowed points in feature space are represented by a constraint set, then we can take those constraints into account when computing AXp's and CXp's. The original ideas on accounting for input constraints were presented in recent work [130], and extended more recently for contrastive explanations [323]. However, a major difficulty with the handling input constraints is how to infer those input constraints in the first place.…”

Section: Input Constraints and Distributionsmentioning

confidence: 99%

“…The size of formal explanations have been addressed by considering probabilistic explanations [18,169,170,312,313]. The effect of input constraints on explainability, that restrict the points in feature space to consider, has been studied in recent works [130,323]. The use of surrogate models for computing formal explanations of complex models has been proposed [57].…”

Section: Introductionmentioning

confidence: 99%

Logic-Based Explainability in Machine Learning

Marques-Silva¹

2022

Preprint

View full text Add to dashboard Cite

The last decade witnessed an ever-increasing stream of successes in Machine Learning (ML). These successes offer clear evidence that ML is bound to become pervasive in a wide range of practical uses, including many that directly affect humans. Unfortunately, the operation of the most successful ML models is incomprehensible for human decision makers. As a result, the use of ML models, especially in highrisk and safety-critical settings is not without concern. In recent years, there have been efforts on devising approaches for explaining ML models. Most of these efforts have focused on so-called model-agnostic approaches. However, all model-agnostic and related approaches offer no guarantees of rigor, hence being referred to as non-formal. For example, such non-formal explanations can be consistent with different predictions, which renders them useless in practice. This paper overviews the ongoing research efforts on computing rigorous model-based explanations of ML models; these being referred to as formal explanations. These efforts encompass a variety of topics, that include the actual definitions of explanations, the characterization of the complexity of computing explanations, the currently best logical encodings for reasoning about different ML models, and also how to make explanations interpretable for human decision makers, among others.

show abstract

Sufficient Reasons for Classifier Decisions in the Presence of Domain Constraints

Cited by 19 publications

References 11 publications

On Tackling Explanation Redundancy in Decision Trees

On Tackling Explanation Redundancy in Decision Trees

No silver bullet: interpretable ML models must be explained

Logic-Based Explainability in Machine Learning

Contact Info

Product

Resources

About