# Towards Aggregating Weighted Feature Attributions

arXiv: https://arxiv.org/abs/1901.10040 · HTML: https://mlsanity.com/paper/1901.10040/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2019.

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

- [The Role of Explainability in Assuring Safety of Machine Learning in Healthcare](https://mlsanity.com/paper/2109.00520/) (2021)
- [Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach](https://mlsanity.com/paper/2111.09121/) (2021)
- [FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanations](https://mlsanity.com/paper/2210.06578/) (2022)
- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)
- [It's FLAN time! Summing feature-wise latent representations for interpretability](https://mlsanity.com/paper/2106.10086/) (2021)
- [NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniques](https://mlsanity.com/paper/2401.17200/) (2024)

## Abstract (arXiv)

Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a training point exerts on a test point, while the latter attempts to attribute value to the features most pertinent to a given prediction. In this work, we discuss an algorithm, AVA: Aggregate Valuation of Antecedents, that fuses these two explanation classes to form a new approach to feature attribution that not only retrieves local explanations but also captures global patterns learned by a model. Our experimentation convincingly favors weighting and aggregating feature attributions via AVA.