Guided-LORE: Improving LORE with a Focused Search of Neighbours

Maaroof, Najlaa; Moreno, Antonio; Valls, Aïda; Jabreel, Mohammed

doi:10.1007/978-3-030-73959-1_4

Cited by 3 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first step of mcFuzzy-LORE is to generate a set of synthetic neighbours of the instance of interest based on the method proposed in C-LORE-F [23]. Second, it constructs a local interpretable FDT model using the induction algorithm proposed in [24].…”

Section: Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

et al. 2023

View full text Add to dashboard Cite

Multi-class classification is a fundamental task in Machine Learning. However, complex models can be viewed as black boxes, making it difficult to gain insight into how the model makes its predictions and build trust in its decision-making process. This paper presents a novel method called Multi-Class Fuzzy-LORE (mcFuzzy-LORE) for explaining the decisions made by multi-class fuzzy-based classifiers such as Fuzzy Random Forests (FRF). mcFuzzy-LORE is an adaptation of the Fuzzy-LORE method that uses fuzzy decision trees as an alternative to classical decision trees, providing interpretable, human-readable rules that describe the reasoning behind the model’s decision for a specific input. The proposed method was evaluated on a private dataset that was used to train an FRF-based multi-class classifier that assesses the risk of developing diabetic retinopathy in diabetic patients. The results show that mcFuzzy-LORE outperforms prior classical LORE-based methods in the generation of counterfactual instances.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

“…The key part of the generation process is the Generate function, which is based on the C-LORE-F method [23]. It defines the neighbours' generation as a search problem and explores the neighbourhood space of a point x by applying a Uniform Cost Search algorithm.…”

Section: Neighbours Generationmentioning

confidence: 99%

Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Although LORE has shown a good performance in explaining classical MLbased systems [6], we believe that it can be improved for the particular case of fuzzy-based systems. In our previous works [7,8] we proposed two extensions of LORE, called Guided-LORE and C-LORE-F. In the former the neighbours' generation step was formalized as a search problem and solved using Uniform Cost Search, whereas in the latter the knowledge about the definition of the fuzzy variables was used to focus the exploration of the neighbours' space.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the promising outcome obtained with Guided-LORE and C-LORE-F, they still have some shortcomings. First, the quality of the obtained counterfactual instances should be improved [7]. Second, the basic explanation in LORE (and its variants) is limited to a single rule derived from the activated path in a decision tree, which is not very informative.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

Maaroof

Moreno

Jabreel

et al. 2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Classification systems based Machine Learning hide the logic of their internal decision processes from the users. Hence, post-hoc explanations about their predictions are often required. This paper proposes Fuzzy-LORE, a method that generates local explanations for fuzzy-based Machine Learning systems. First, it learns a local fuzzy decision tree using a set of synthetic neighbours from the input instance. Then, it extracts from the logic of the fuzzy decision tree a meaningful explanation consisting of a set of decision rules (which explain the reasons behind the decision), a set of counterfactual rules (which inform of small changes in the instance’s features that would lead to a different outcome), and finally a set of specific counterfactual examples. Our experiments on a real-world medical dataset show that Fuzzy-LORE outperforms prior approaches and methods for generating local explanations.

show abstract

“…In a previous work [12] we proposed Guided-LORE, an adaptation of the LORE method in which the neighbourhood generation, which is the key in obtaining a solid explanation, was formalised as a search problem and solved using Uniform Cost Search. Such adaptation allowed us, to some extent, to make the generation process more informed.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Two Rule-Based Explanation Methods for Diabetic Retinopathy Risk Assessment

et al. 2022

Self Cite

View full text Add to dashboard Cite

Understanding the reasons behind the decisions of complex intelligent systems is crucial in many domains, especially in healthcare. Local explanation models analyse a decision on a single instance, by using the responses of the system to the points in its neighbourhood to build a surrogate model. This work makes a comparative analysis of the local explanations provided by two rule-based explanation methods on RETIPROGRAM, a system based on a fuzzy random forest that analyses the health record of a diabetic person to assess his/her degree of risk of developing diabetic retinopathy. The analysed explanation methods are C-LORE-F (a variant of LORE that builds a decision tree) and DRSA (a method based on rough sets that builds a set of rules). The explored methods gave good results in several metrics, although there is room for improvement in the generation of counterfactual examples.

show abstract

Guided-LORE: Improving LORE with a Focused Search of Neighbours

Cited by 3 publications

References 13 publications

Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

A Comparative Study of Two Rule-Based Explanation Methods for Diabetic Retinopathy Risk Assessment

Contact Info

Product

Resources

About