# Global Aggregations of Local Explanations for Black Box models

arXiv: https://arxiv.org/abs/1907.03039 · HTML: https://mlsanity.com/paper/1907.03039/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2019.

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

- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Explanations in Autonomous Driving: A Survey](https://mlsanity.com/paper/2103.05154/) (2021)
- [Best of both worlds: local and global explanations with human-understandable concepts](https://mlsanity.com/paper/2106.08641/) (2021)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [Statistical Significance of Feature Importance Rankings](https://mlsanity.com/paper/2401.15800/) (2024)
- [Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study](https://mlsanity.com/paper/2109.00707/) (2021)
- [Accelerating the Global Aggregation of Local Explanations](https://mlsanity.com/paper/2312.07991/) (2023)
- [Towards Interpretability in Audio and Visual Affective Machine Learning: A Review](https://mlsanity.com/paper/2306.08933/) (2023)
- [Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables](https://mlsanity.com/paper/2405.15661/) (2024)
- [Axiomatic Characterisations of Sample-based Explainers](https://mlsanity.com/paper/2408.04903/) (2024)
- [MusicLIME: Explainable Multimodal Music Understanding](https://mlsanity.com/paper/2409.10496/) (2024)
- [Faithful and Plausible Explanations of Medical Code Predictions](https://mlsanity.com/paper/2104.07894/) (2021)
- [Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners](https://mlsanity.com/paper/2202.01153/) (2022)
- [Data augmentation and explainability for bias discovery and mitigation in deep learning](https://mlsanity.com/paper/2308.09464/) (2023)
- [CohEx: A Generalized Framework for Cohort Explanation](https://mlsanity.com/paper/2410.13190/) (2024)
- [Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration](https://mlsanity.com/paper/2505.00802/) (2025)
- [Explainable AI does not provide the explanations end-users are asking for](https://mlsanity.com/paper/2302.11577/) (2023)
- [How to safely discard features based on aggregate SHAP values](https://mlsanity.com/paper/2503.23111/) (2025)
- [Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification](https://mlsanity.com/paper/2506.23247/) (2025)
- [CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation](https://mlsanity.com/paper/2512.06814/) (2025)
- [Fairness of Machine Learning Algorithms in Demography](https://mlsanity.com/paper/2202.01013/) (2022)
- [Evaluating the overall sensitivity of saliency-based explanation methods](https://mlsanity.com/paper/2306.13682/) (2023)
- [Integrated feature analysis for deep learning interpretation and class activation maps](https://mlsanity.com/paper/2407.01142/) (2024)
- [NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers](https://mlsanity.com/paper/2407.01697/) (2024)
- [Explaining word embeddings with perfect fidelity: Case study in research impact prediction](https://mlsanity.com/paper/2409.15912/) (2024)
- [Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks](https://mlsanity.com/paper/2504.15479/) (2025)
- [Implet: A Post-hoc Subsequence Explainer for Time Series Models](https://mlsanity.com/paper/2505.08748/) (2025)
- [Multi-criteria Rank-based Aggregation for Explainable AI](https://mlsanity.com/paper/2505.24612/) (2025)
- [L2GTX: From Local to Global Time Series Explanations](https://mlsanity.com/paper/2603.13065/) (2026)
- [SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events](https://mlsanity.com/paper/2608.20117/) (2026)

## Abstract (arXiv)

The decision-making process of many state-of-the-art machine learning models is inherently inscrutable to the extent that it is impossible for a human to interpret the model directly: they are black box models. This has led to a call for research on explaining black box models, for which there are two main approaches. Global explanations that aim to explain a model's decision making process in general, and local explanations that aim to explain a single prediction. Since it remains challenging to establish fidelity to black box models in globally interpretable approximations, much attention is put on local explanations. However, whether local explanations are able to reliably represent the black box model and provide useful insights remains an open question. We present Global Aggregations of Local Explanations (GALE) with the objective to provide insights in a model's global decision making process. Overall, our results reveal that the choice of aggregation matters. We find that the global importance introduced by Local Interpretable Model-agnostic Explanations (LIME) does not reliably represent the model's global behavior. Our proposed aggregations are better able to represent how features affect the model's predictions, and to provide global insights by identifying distinguishing features.