# Global Explanations of Neural Networks: Mapping the Landscape of Predictions

arXiv: https://arxiv.org/abs/1902.02384 · HTML: https://mlsanity.com/paper/1902.02384/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2019.

## Built on by (most cited first, 30 of 32)

- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations](https://mlsanity.com/paper/2205.07277/) (2022)
- [Auxiliary Losses for Learning Generalizable Concept-based Models](https://mlsanity.com/paper/2311.11108/) (2023)
- [Best of both worlds: local and global explanations with human-understandable concepts](https://mlsanity.com/paper/2106.08641/) (2021)
- [Explainable AI for Bioinformatics: Methods, Tools, and Applications](https://mlsanity.com/paper/2212.13261/) (2022)
- [Gaussian Process Neural Additive Models](https://mlsanity.com/paper/2402.12518/) (2024)
- [SketchXAI: A First Look at Explainability for Human Sketches](https://mlsanity.com/paper/2304.11744/) (2023)
- [On the Emergence of Symmetrical Reality](https://mlsanity.com/paper/2401.15132/) (2024)
- [Feature Importance Explanations for Temporal Black-Box Models](https://mlsanity.com/paper/2102.11934/) (2021)
- [Counterfactual Explanations via Latent Space Projection and Interpolation](https://mlsanity.com/paper/2112.00890/) (2021)
- [Four Axiomatic Characterizations of the Integrated Gradients Attribution Method](https://mlsanity.com/paper/2306.13753/) (2023)
- [What Makes a Scientific Paper be Accepted for Publication?](https://mlsanity.com/paper/2104.07112/) (2021)
- [Interpretable Summaries of Black Box Incident Triaging with Subgroup Discovery](https://mlsanity.com/paper/2108.03013/) (2021)
- [Finding Representative Interpretations on Convolutional Neural Networks](https://mlsanity.com/paper/2108.06384/) (2021)
- [ShapG: new feature importance method based on the Shapley value](https://mlsanity.com/paper/2407.00506/) (2024)
- [Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability](https://mlsanity.com/paper/2305.03100/) (2023)
- [Implementing local-explainability in Gradient Boosting Trees: Feature Contribution](https://mlsanity.com/paper/2402.09197/) (2024)
- [SIDEs: Separating Idealization from Deceptive Explanations in xAI](https://mlsanity.com/paper/2404.16534/) (2024)
- [FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations](https://mlsanity.com/paper/2412.07313/) (2024)
- [Feature construction using explanations of individual predictions](https://mlsanity.com/paper/2301.09631/) (2023)
- [On Model Explanations with Transferable Neural Pathways](https://mlsanity.com/paper/2309.09887/) (2023)
- [Model Interpretation and Explainability: Towards Creating Transparency in Prediction Models](https://mlsanity.com/paper/2405.20794/) (2024)
- [Linking Model Intervention to Causal Interpretation in Model Explanation](https://mlsanity.com/paper/2410.15648/) (2024)
- [A Unified Concept-Based System for Local, Global, and Misclassification Explanations](https://mlsanity.com/paper/2306.03531/) (2023)
- [Evaluating the overall sensitivity of saliency-based explanation methods](https://mlsanity.com/paper/2306.13682/) (2023)
- [Advancing Explainable AI Toward Human-Like Intelligence: Forging the Path to Artificial Brain](https://mlsanity.com/paper/2402.06673/) (2024)
- [Upside-Down Reinforcement Learning for More Interpretable Optimal Control](https://mlsanity.com/paper/2411.11457/) (2024)
- [On Measuring Intrinsic Causal Attributions in Deep Neural Networks](https://mlsanity.com/paper/2505.09660/) (2025)

## Abstract (arXiv)

A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduce neural network decisions to a single set of features. In response, we present an approach for generating global attributions called GAM, which explains the landscape of neural network predictions across subpopulations. GAM augments global explanations with the proportion of samples that each attribution best explains and specifies which samples are described by each attribution. Global explanations also have tunable granularity to detect more or fewer subpopulations. We demonstrate that GAM's global explanations 1) yield the known feature importances of simulated data, 2) match feature weights of interpretable statistical models on real data, and 3) are intuitive to practitioners through user studies. With more transparent predictions, GAM can help ensure neural network decisions are generated for the right reasons.