2021
DOI: 10.1007/978-3-030-73959-1_4
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(6 citation statements)
references
References 13 publications
0
6
0
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
“…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%
“…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%
“…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%
“…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%