# Model Agnostic Contrastive Explanations for Structured Data

arXiv: https://arxiv.org/abs/1906.00117 · HTML: https://mlsanity.com/paper/1906.00117/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2019.

## Built on by (most cited first, 30 of 41)

- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark](https://mlsanity.com/paper/2402.11592/) (2024)
- [Towards Robust and Reliable Algorithmic Recourse](https://mlsanity.com/paper/2102.13620/) (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)
- [DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training](https://mlsanity.com/paper/2310.02025/) (2023)
- [NICE: An Algorithm for Nearest Instance Counterfactual Explanations](https://mlsanity.com/paper/2104.07411/) (2021)
- [Synthetic Benchmarks for Scientific Research in Explainable Machine Learning](https://mlsanity.com/paper/2106.12543/) (2021)
- [Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures](https://mlsanity.com/paper/2410.07698/) (2024)
- [CLEAR: Generative Counterfactual Explanations on Graphs](https://mlsanity.com/paper/2210.08443/) (2022)
- [Amortized Generation of Sequential Algorithmic Recourses for Black-box Models](https://mlsanity.com/paper/2106.03962/) (2021)
- [Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning](https://mlsanity.com/paper/2502.03304/) (2025)
- [Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI](https://mlsanity.com/paper/2204.10152/) (2022)
- [A survey and taxonomy of loss functions in machine learning](https://mlsanity.com/paper/2301.05579/) (2023)
- [MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation](https://mlsanity.com/paper/2205.15540/) (2022)
- [Let the CAT out of the bag: Contrastive Attributed explanations for Text](https://mlsanity.com/paper/2109.07983/) (2021)
- [Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training](https://mlsanity.com/paper/2504.20314/) (2025)
- [CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows](https://mlsanity.com/paper/2303.14668/) (2023)
- [On Quantitative Evaluations of Counterfactuals](https://mlsanity.com/paper/2111.00177/) (2021)
- [Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing](https://mlsanity.com/paper/2404.00158/) (2024)
- [Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion](https://mlsanity.com/paper/2312.13616/) (2023)
- [Rendering Wireless Environments Useful for Gradient Estimators: A Zero-Order Stochastic Federated Learning Method](https://mlsanity.com/paper/2401.17460/) (2024)
- [Trust Regions for Explanations via Black-Box Probabilistic Certification](https://mlsanity.com/paper/2402.11168/) (2024)
- [Sanity checks and improvements for patch visualisation in prototype-based image classification](https://mlsanity.com/paper/2302.08508/) (2023)
- [End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost](https://mlsanity.com/paper/2509.00031/) (2025)
- [ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization](https://mlsanity.com/paper/2603.14254/) (2026)
- [Contrastive Explanations for Explaining Model Adaptations](https://mlsanity.com/paper/2104.02459/) (2021)
- [Causality-based Counterfactual Explanation for Classification Models](https://mlsanity.com/paper/2105.00703/) (2021)
- [Post-discovery Analysis of Anomalous Subsets](https://mlsanity.com/paper/2111.14622/) (2021)
- [Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning](https://mlsanity.com/paper/2201.12143/) (2022)
- [Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposal](https://mlsanity.com/paper/2302.03180/) (2023)

## Abstract (arXiv)

Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive Explanations Method (MACEM), to generate contrastive explanations for any classification model where one is able to only query the class probabilities for a desired input. This allows us to generate contrastive explanations for not only neural networks, but models such as random forests, boosted trees and even arbitrary ensembles that are still amongst the state-of-the-art when learning on structured data [13]. Moreover, to obtain meaningful explanations we propose a principled approach to handle real and categorical features leading to novel formulations for computing pertinent positives and negatives that form the essence of a contrastive explanation. A detailed treatment of the different data types of this nature was not performed in the previous work, which assumed all features to be positive real valued with zero being indicative of the least interesting value. We part with this strong implicit assumption and generalize these methods so as to be applicable across a much wider range of problem settings. We quantitatively and qualitatively validate our approach over 5 public datasets covering diverse domains.