# Interpreting Classifiers through Attribute Interactions in Datasets

arXiv: https://arxiv.org/abs/1707.07576 · HTML: https://mlsanity.com/paper/1707.07576/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2017.

## Built on by (most cited first, 8 of 8)

- [PredDiff: Explanations and Interactions from Conditional Expectations](https://mlsanity.com/paper/2102.13519/) (2021)
- [SLISEMAP: Supervised dimensionality reduction through local explanations](https://mlsanity.com/paper/2201.04455/) (2022)
- [Sharing pattern submodels for prediction with missing values](https://mlsanity.com/paper/2206.11161/) (2022)
- [Coalitional strategies for efficient individual prediction explanation](https://mlsanity.com/paper/2104.00765/) (2021)
- [Feature construction using explanations of individual predictions](https://mlsanity.com/paper/2301.09631/) (2023)
- [Review of Explainable Graph-Based Recommender Systems](https://mlsanity.com/paper/2408.00166/) (2024)
- [Towards an Explanation Space to Align Humans and Explainable-AI Teamwork](https://mlsanity.com/paper/2106.01503/) (2021)
- [Harnessing value from data science in business: ensuring explainability and fairness of solutions](https://mlsanity.com/paper/2108.07714/) (2021)

## Abstract (arXiv)

In this work we present the novel ASTRID method for investigating which attribute interactions classifiers exploit when making predictions. Attribute interactions in classification tasks mean that two or more attributes together provide stronger evidence for a particular class label. Knowledge of such interactions makes models more interpretable by revealing associations between attributes. This has applications, e.g., in pharmacovigilance to identify interactions between drugs or in bioinformatics to investigate associations between single nucleotide polymorphisms. We also show how the found attribute partitioning is related to a factorisation of the data generating distribution and empirically demonstrate the utility of the proposed method.