LORE Stable and Actionable

Overview

Recent years have witnessed the rise of accurate but obscure classification models that hide the logic of their internal decision processes. Explaining the decision taken by a black-box classifier on a specific input instance is therefore of striking interest.

We propose LORE-SA (LOcal Rule-based Explanations with Stability and Actionability), a local rule-based model-agnostic explanation method providing stable and actionable explanations (Riccardo et al., 2018; Guidotti et al., 2022).

Key Features

An explanation provided by LORE-SA consists of:

Factual logic rule: States the reasons for the black-box decision on the specific instance
Actionable counterfactual logic rules: Proactively suggest changes to the instance that would lead to a different outcome

These features make LORE-SA particularly valuable for real-world applications where understanding “why” and “what if” questions are crucial for decision-making.

Methodology

Explanations are computed from a decision tree that mimics the behavior of the black-box locally to the instance under investigation. The approach follows these key steps:

Neighborhood Generation: Synthetic neighbor instances are generated through a genetic algorithm whose fitness function is driven by the black-box behavior
Ensemble Learning: An ensemble of decision trees is learned from neighborhoods of the instance under investigation
Tree Merging: The ensemble is merged into a single decision tree through a bagging-like approach that favors both stability and fidelity

This innovative methodology ensures that explanations remain consistent across similar instances while maintaining high fidelity to the original black-box model’s behavior.

Results

Extensive experiments demonstrate that LORE-SA advances the state-of-the-art towards a comprehensive approach that successfully covers:

Stability: Consistent explanations across similar instances
Actionability: Practical counterfactual suggestions for decision change
Fidelity: Accurate representation of the black-box model’s local behavior
Interpretability: Human-understandable logic rules

The method provides a balanced solution for factual and counterfactual explanations, making it a powerful tool for understanding and interacting with complex classification models.

References

2022

Stable and actionable explanations of black-box models through factual and counterfactual rules

Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Francesca Naretto, Franco Turini, and 2 more authors

Data Mining and Knowledge Discovery, Nov 2022

RESEARCH LINE
1

2

Abs Bib HTML

Recent years have witnessed the rise of accurate but obscure classification models that hide the logic of their internal decision processes. Explaining the decision taken by a black-box classifier on a specific input instance is therefore of striking interest. We propose a local rule-based model-agnostic explanation method providing stable and actionable explanations. An explanation consists of a factual logic rule, stating the reasons for the black-box decision, and a set of actionable counterfactual logic rules, proactively suggesting the changes in the instance that lead to a different outcome. Explanations are computed from a decision tree that mimics the behavior of the black-box locally to the instance to explain. The decision tree is obtained through a bagging-like approach that favors stability and fidelity: first, an ensemble of decision trees is learned from neighborhoods of the instance under investigation; then, the ensemble is merged into a single decision tree. Neighbor instances are synthetically generated through a genetic algorithm whose fitness function is driven by the black-box behavior. Experiments show that the proposed method advances the state-of-the-art towards a comprehensive approach that successfully covers stability and actionability of factual and counterfactual explanations.
@article{GMR2022, author = {Guidotti, Riccardo and Monreale, Anna and Ruggieri, Salvatore and Naretto, Francesca and Turini, Franco and Pedreschi, Dino and Giannotti, Fosca}, doi = {10.1007/s10618-022-00878-5}, issn = {1573-756X}, journal = {Data Mining and Knowledge Discovery}, line = {1,2}, month = nov, number = {5}, open_access = {Gold}, pages = {2825–2862}, publisher = {Springer Science and Business Media LLC}, title = {Stable and actionable explanations of black-box models through factual and counterfactual rules}, visible_on_website = {YES}, volume = {38}, year = {2022} }

2018

Local Rule-Based Explanations of Black Box Decision Systems

Guidotti Riccardo, Monreale Anna, Ruggieri Salvatore, Pedreschi Dino, Turini Franco, and 1 more author

Dec 2018

RESEARCH LINE
1

Abs Bib HTML

The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of explanations for the decisions of black box systems is a key ethical issue, and a limitation to the adoption of achine learning components in socially sensitive and safety-critical contexts. Therefore, we need explanations that reveals the reasons why a predictor takes a certain decision. In this paper we focus on the problem of black box outcome explanation, i.e., explaining the reasons of the decision taken on a specific instance. We propose LORE, an agnostic method able to provide interpretable and faithful explanations. LORE first leans a local interpretable predictor on a synthetic neighborhood generated by a genetic algorithm. Then it derives from the logic of the local interpretable predictor a meaningful explanation consisting of: a decision rule, which explains the reasons of the decision; and a set of counterfactual rules, suggesting the changes in the instance’s features that lead to a different outcome. Wide experiments show that LORE outperforms existing methods and baselines both in the quality of explanations and in the accuracy in mimicking the black box.
@misc{GMR2018a, author = {Riccardo, Guidotti and Anna, Monreale and Salvatore, Ruggieri and Dino, Pedreschi and Franco, Turini and Fosca, Giannotti}, doi = {1805.10820}, line = {1}, month = dec, publisher = {Arxive}, title = {Local Rule-Based Explanations of Black Box Decision Systems}, year = {2018} }