FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
Model interpretability has become an important problem in machine learning (ML) due to the increased effect that algorithmic decisions have on humans. Counterfactual explanations can help users understand not only why ML models make certain decisions, but also how these decisions can be changed. We frame the problem of finding counterfactual explanations as a gradient-based optimization task and extend previous work that could only be applied to differentiable models. In order to accommodate non-differentiable models such as tree ensembles, we use probabilistic model approximations in the optimization framework. We introduce an approximation technique that is effective for finding counterfactual explanations for predictions of the original model and show that our counterfactual examples are significantly closer to the original instances than those produced by other methods specifically designed for tree ensembles.
Code (1)
Tasks
counterfactualMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
Scope of Reproducibility This study aims to reproduce the results of the paper 'FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles' by Lucic et al. The main claims of the original paper are that …
Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms
We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier. This has become a topic of recent inter…
counterfactualFlexible Counterfactual Explanations with Generative Models
Counterfactual explanations provide actionable insights to achieve desired outcomes by suggesting minimal changes to input features. However, existing methods rely on fixed sets of mutable features, which makes counterfa…
counterfactualOptimal Counterfactual Explanations in Tree Ensembles
Counterfactual explanations are usually generated through heuristics that are sensitive to the search's initial conditions. The absence of guarantees of performance and robustness hinders trustworthiness. In this paper, …
counterfactualCounterfactual ExplanationInterpretable Machine LearningTemporal Counterfactual Explanations of Behaviour Tree Decisions
Explainability, in particular, the ability for robots to explain why they have made a decision or behaved in a certain way, is a critical tool in helping users understand the robots they interact and coexist with. Behavi…