Corpus ID: 195820639

Interpretable Counterfactual Explanations Guided by Prototypes

@article{Looveren2019InterpretableCE,
  title={Interpretable Counterfactual Explanations Guided by Prototypes},
  author={A. V. Looveren and Janis Klaise},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.02584}
}
We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and result in more interpretable explanations. We introduce two novel metrics to quantitatively evaluate local interpretability at the instance level. We use these metrics to… Expand
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Conditional Generative Models for Counterfactual Explanations
BEYOND TRIVIAL COUNTERFACTUAL GENERATIONS
  • 2020
SCOUT: Self-Aware Discriminant Counterfactual Explanations
  • Pei Wang, N. Vasconcelos
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning
ECINN: Efficient Counterfactuals from Invertible Neural Networks
Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
Explaining machine learning classifiers through diverse counterfactual explanations
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
TIP: Typifying the Interpretability of Procedures
Examples are not enough, learn to criticize! Criticism for Interpretability
Anchors: High-Precision Model-Agnostic Explanations
Interpreting Black Box Predictions using Fisher Kernels
Generating Contrastive Explanations with Monotonic Attribute Functions
Prototypical Networks for Few-shot Learning
...
1
2
3
4
...