# Do intermediate feature coalitions aid explainability of black-box models?

arXiv: https://arxiv.org/abs/2303.11920 · HTML: https://mlsanity.com/paper/2303.11920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 6 of 6)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [groupShapley: Efficient prediction explanation with Shapley values for feature groups](https://mlsanity.com/paper/2106.12228/) (2021)
- [Contextual Importance and Utility: aTheoretical Foundation](https://mlsanity.com/paper/2202.07292/) (2022)
- [Explainability in autonomous pedagogically structured scenarios](https://mlsanity.com/paper/2210.12140/) (2022)
- [Modelling Control Arguments via Cooperation Logic in Unforeseen Scenarios](https://mlsanity.com/paper/2210.12114/) (2022)
- [Towards Preserving Semantic Structure in Argumentative Multi-Agent via Abstract Interpretation](https://mlsanity.com/paper/2211.15782/) (2022)

## Abstract (arXiv)

This work introduces the notion of intermediate concepts based on levels structure to aid explainability for black-box models. The levels structure is a hierarchical structure in which each level corresponds to features of a dataset (i.e., a player-set partition). The level of coarseness increases from the trivial set, which only comprises singletons, to the set, which only contains the grand coalition. In addition, it is possible to establish meronomies, i.e., part-whole relationships, via a domain expert that can be utilised to generate explanations at an abstract level. We illustrate the usability of this approach in a real-world car model example and the Titanic dataset, where intermediate concepts aid in explainability at different levels of abstraction.