NICE: An Algorithm for Nearest Instance Counterfactual Explanations

by   Dieter Brughmans, et al.

In this paper we suggest NICE: a new algorithm to generate counterfactual explanations for heterogeneous tabular data. The design of our algorithm specifically takes into account algorithmic requirements that often emerge in real-life deployments: the ability to provide an explanation for all predictions, being efficient in run-time, and being able to handle any classification model (also non-differentiable ones). More specifically, our approach exploits information from a nearest instance tospeed up the search process. We propose four versions of NICE, where three of them optimize the explanations for one of the following properties: sparsity, proximity or plausibility. An extensive empirical comparison on 10 datasets shows that our algorithm performs better on all properties than the current state-of-the-art. These analyses show a trade-off between on the one hand plausiblity and on the other hand proximity or sparsity, with our different optimization methods offering the choice to select the preferred trade-off. An open-source implementation of NICE can be found at


DeDUCE: Generating Counterfactual Explanations Efficiently

When an image classifier outputs a wrong class label, it can be helpful ...

GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations

Counterfactual explanations have been widely studied in explainability, ...

FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanations

Counterfactual explanations have substantially increased in popularity i...

MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation

Counterfactual explanation is an important Explainable AI technique to e...

Counterfactual Explanation Algorithms for Behavioral and Textual Data

We study the interpretability of predictive systems that use high-dimens...

Navigating Explanatory Multiverse Through Counterfactual Path Geometry

Counterfactual explanations are the de facto standard when tasked with i...

Probabilistic DL Reasoning with Pinpointing Formulas: A Prolog-based Approach

When modeling real world domains we have to deal with information that i...

Please sign up or login with your details

Forgot password? Click here to reset