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

arXiv: https://arxiv.org/abs/2210.06578 · HTML: https://mlsanity.com/paper/2210.06578/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 16 of 16)

- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [Learning Model-Agnostic Counterfactual Explanations for Tabular Data](https://mlsanity.com/paper/1910.09398/) (2019)
- [The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons](https://mlsanity.com/paper/1912.04930/) (2019)
- [Counterfactual Explanations Can Be Manipulated](https://mlsanity.com/paper/2106.02666/) (2021)
- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Towards causal benchmarking of bias in face analysis algorithms](https://mlsanity.com/paper/2007.06570/) (2020)
- [On the Adversarial Robustness of Causal Algorithmic Recourse](https://mlsanity.com/paper/2112.11313/) (2021)
- [On the computation of counterfactual explanations -- A survey](https://mlsanity.com/paper/1911.07749/) (2019)
- [GeCo: Quality Counterfactual Explanations in Real Time](https://mlsanity.com/paper/2101.01292/) (2021)
- [xGEMs: Generating Examplars to Explain Black-Box Models](https://mlsanity.com/paper/1806.08867/) (2018)
- [Latent-CF: A Simple Baseline for Reverse Counterfactual Explanations](https://mlsanity.com/paper/2012.09301/) (2020)
- [Towards Aggregating Weighted Feature Attributions](https://mlsanity.com/paper/1901.10040/) (2019)
- [Counterfactual Explanations via Latent Space Projection and Interpolation](https://mlsanity.com/paper/2112.00890/) (2021)

## Built on by (most cited first, 6 of 6)

- [Robust Counterfactual Explanations in Machine Learning: A Survey](https://mlsanity.com/paper/2402.01928/) (2024)
- [SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies](https://mlsanity.com/paper/2404.18326/) (2024)
- [Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse](https://mlsanity.com/paper/2410.02273/) (2024)
- [On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations](https://mlsanity.com/paper/2307.06941/) (2023)
- [Improving Decision Sparsity](https://mlsanity.com/paper/2410.20483/) (2024)
- [From Student Risk Prediction to SC2R: Semantics-Constrained Counterfactual Recourse for Educational Decision Support](https://mlsanity.com/paper/2608.17618/) (2026)

## Abstract (arXiv)

Counterfactual explanations have substantially increased in popularity in the past few years as a useful human-centric way of understanding individual black-box model predictions. While several properties desired of high-quality counterfactuals have been identified in the literature, three crucial concerns: the speed of explanation generation, robustness/sensitivity and succinctness of explanations (sparsity) have been relatively unexplored. In this paper, we present FASTER-CE: a novel set of algorithms to generate fast, sparse, and robust counterfactual explanations. The key idea is to efficiently find promising search directions for counterfactuals in a latent space that is specified via an autoencoder. These directions are determined based on gradients with respect to each of the original input features as well as of the target, as estimated in the latent space. The ability to quickly examine combinations of the most promising gradient directions as well as to incorporate additional user-defined constraints allows us to generate multiple counterfactual explanations that are sparse, realistic, and robust to input manipulations. Through experiments on three datasets of varied complexities, we show that FASTER-CE is not only much faster than other state of the art methods for generating multiple explanations but also is significantly superior when considering a larger set of desirable (and often conflicting) properties. Specifically we present results across multiple performance metrics: sparsity, proximity, validity, speed of generation, and the robustness of explanations, to highlight the capabilities of the FASTER-CE family.