# Human-interpretable model explainability on high-dimensional data

arXiv: https://arxiv.org/abs/2010.07384 · HTML: https://mlsanity.com/paper/2010.07384/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

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

- [Grouped Feature Importance and Combined Features Effect Plot](https://mlsanity.com/paper/2104.11688/) (2021)
- [Does Your Model Think Like an Engineer? Explainable AI for Bearing Fault Detection with Deep Learning](https://mlsanity.com/paper/2310.12967/) (2023)
- [Combining Counterfactuals With Shapley Values To Explain Image Models](https://mlsanity.com/paper/2206.07087/) (2022)
- [The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research](https://mlsanity.com/paper/2310.07882/) (2023)
- [Latent SHAP: Toward Practical Human-Interpretable Explanations](https://mlsanity.com/paper/2211.14797/) (2022)
- [FINCH: Locally Visualizing Higher-Order Feature Interactions in Black Box Models](https://mlsanity.com/paper/2503.16445/) (2025)
- [The hunt for new pulsating ultraluminous X-ray sources: a clustering approach](https://mlsanity.com/paper/2507.15032/) (2025)
- [ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values](https://mlsanity.com/paper/2604.11200/) (2026)

## Abstract (arXiv)

The importance of explainability in machine learning continues to grow, as both neural-network architectures and the data they model become increasingly complex. Unique challenges arise when a model's input features become high dimensional: on one hand, principled model-agnostic approaches to explainability become too computationally expensive; on the other, more efficient explainability algorithms lack natural interpretations for general users. In this work, we introduce a framework for human-interpretable explainability on high-dimensional data, consisting of two modules. First, we apply a semantically meaningful latent representation, both to reduce the raw dimensionality of the data, and to ensure its human interpretability. These latent features can be learnt, e.g. explicitly as disentangled representations or implicitly through image-to-image translation, or they can be based on any computable quantities the user chooses. Second, we adapt the Shapley paradigm for model-agnostic explainability to operate on these latent features. This leads to interpretable model explanations that are both theoretically controlled and computationally tractable. We benchmark our approach on synthetic data and demonstrate its effectiveness on several image-classification tasks.