LoRMIkA: Local rule-based model interpretability with k-optimal associations

Rajapaksha, Dilini; Bergmeir, Christoph; Buntine, Wray L.

doi:10.1016/j.ins.2020.05.126

Cited by 30 publications

(21 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also compute the number of counterfactuals and their best minimal distance to the factual explanation to assess the relevance of counterfactuals. Rajapaksha et al consider coverage (as an indicator of representativeness of a rule for a given dataset), confidence (i.e., the percentage of instances in the dataset which contain the consequent and antecedent together over the number of instances which only contain the antecedent), lift (i.e., an association between antecedent and consequent), leverage (i.e., the observed frequency between the antecedent and consequent), and the number of features in explanation for evaluating their framework against other rule-based methods [152]. Also, White and Garcez reintroduce fidelity to the underlying classifier on the basis of distance to the decision boundary [160].…”

Section: ) Evaluation Methodsmentioning

confidence: 99%

“…Laugel et al measure how justified counterfactuals are by averaging a binary score (one if the explanation is justified following the proposed definition, zero otherwise) over all the generated explanations [100], [144]. It is worth noting that the run-time of explanation generation algorithms is reported in addition to the evaluation metrics for several frameworks [132], [139], [146], [152], [156], [159].…”

Section: ) Evaluation Methodsmentioning

confidence: 99%

“…Indeed, contfactuals are particularly suitable for informing the end-user why a given data example is assigned a particular class label. Thus, the outlined classification-oriented frameworks are evaluated on classifiers based on logistic regression [55], [136], [153], [158], decision trees [46], [80], [122], [140], [150], [155], [159], gradient boosted decision trees [147], support vector machines [131], [138], [146], random forests [81], [86], [142]- [144], neural networks [6], [48], [49], [91], [129], [130], [133], [135], [139], [141], [145], [148], [151], or combinations of these [100], [105], [134], [152], [154], [160]. In three studies [67], [128], [137], the classifiers used in the experiments are not specified.…”

Section: ) Ai Problemmentioning

confidence: 99%

“…They can be extracted from interpretable featurevalue pairs as a result of pruning in the search space [132]. In addition, they can replicate the internals of the classifier's structure, e.g., in the form of decision tree nodes or rules [80], [140], [152].…”

Section: ) Output Representationmentioning

confidence: 99%

See 3 more Smart Citations

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

et al. 2021

View full text Add to dashboard Cite

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

show abstract

Section: ) Evaluation Methodsmentioning

confidence: 99%

Section: ) Evaluation Methodsmentioning

confidence: 99%

Section: ) Ai Problemmentioning

confidence: 99%

Section: ) Output Representationmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

et al. 2021

View full text Add to dashboard Cite

show abstract

“…al introduced MUSE [10] which uses rules to explain model behaviors in user-defined subspaces. More recently, LoRMIkA [11] extracts k-optimal association rules to explain the model predictions for classification data sets.…”

Section: Surrogate Modelsmentioning

confidence: 99%

Visual Exploration of Machine Learning Model Behavior with Hierarchical Surrogate Rule Sets

Yuan¹,

Barr²,

Overton³

et al. 2022

Preprint

View full text Add to dashboard Cite

One of the potential solutions for model interpretation is to train a surrogate model: a more transparent model that approximates the behavior of the model to be explained. Typically, classification rules or decision trees are used due to the intelligibility of their logic-based expressions. However, decision trees can grow too deep and rule sets can become too large to approximate a complex model. Unlike paths on a decision tree that must share ancestor nodes (conditions), rules are more flexible. However, the unstructured visual representation of rules makes it hard to make inferences across rules. To address these issues, we present a workflow that includes novel algorithmic and interactive solutions. First, we present Hierarchical Surrogate Rules (HSR), an algorithm that generates hierarchical rules based on user-defined parameters. We also contribute SURE, a visual analytics (VA) system that integrates HSR and interactive surrogate rule visualizations. Particularly, we present a novel feature-aligned tree to overcome the shortcomings of existing rule visualizations. We evaluate the algorithm in terms of parameter sensitivity, time performance, and comparison with surrogate decision trees and find that it scales reasonably well and outperforms decision trees in many respects. We also evaluate the visualization and the VA system by a usability study with 24 volunteers and an observational study with 7 domain experts. Our investigation shows that the participants can use feature-aligned trees to perform non-trivial tasks with very high accuracy. We also discuss many interesting observations that can be useful for future research on designing effective rule-based VA systems.

show abstract

Explainable artificial intelligence: a comprehensive review

et al. 2021

View full text Add to dashboard Cite

Thanks to the exponential growth in computing power and vast amounts of data, artificial intelligence (AI) has witnessed remarkable developments in recent years, enabling it to be ubiquitously adopted in our daily lives. Even though AI-powered systems have brought competitive advantages, the black-box nature makes them lack transparency and prevents them from explaining their decisions. This issue has motivated the introduction of explainable artificial intelligence (XAI), which promotes AI algorithms that can show their internal process and explain how they made decisions. The number of XAI research has increased significantly in recent years, but there lacks a unified and comprehensive review of the latest XAI progress. This review aims to bridge the gap by discovering the critical perspectives of the rapidly growing body of research associated with XAI. After offering the readers a solid XAI background, we analyze and review various XAI methods, which are grouped into (i) pre-modeling explainability, (ii) interpretable model, and (iii) post-modeling explainability. We also pay attention to the current methods that dedicate to interpret and analyze deep learning methods. In addition, we systematically discuss various XAI challenges, such as the trade-off between the performance and the explainability, evaluation methods, security, and policy. Finally, we show the standard approaches that are leveraged to deal with the mentioned challenges.

show abstract

LoRMIkA: Local rule-based model interpretability with k-optimal associations

Cited by 30 publications

References 20 publications

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

Visual Exploration of Machine Learning Model Behavior with Hierarchical Surrogate Rule Sets

Explainable artificial intelligence: a comprehensive review

Contact Info

Product

Resources

About