Axiomatic Explainer Globalness via Optimal Transport
Not on the map. Why?
Abstract (arXiv)
Explainability methods are often challenging to evaluate and compare. With a multitude of explainers available, practitioners must often compare and select explainers based on quantitative evaluation metrics. One particular differentiator between explainers is the diversity of explanations for a given dataset; i.e. whether all explanations are identical, unique and uniformly distributed, or somewhere between these two extremes. In this work, we define a complexity measure for explainers, globalness, which enables deeper understanding of the distribution of explanations produced by feature attribution and feature selection methods for a given dataset. We establish the axiomatic properties that any such measure should possess and prove that our proposed measure, Wasserstein Globalness, meets these criteria. We validate the utility of Wasserstein Globalness using image, tabular, and synthetic datasets, empirically showing that it both facilitates meaningful comparison between explainers and improves the selection process for explainability methods.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 90 references that are in the map. First posted on arXiv 2 Nov 2024.
Builds on
49 of 90 references.
References · 49
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
- 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
37 more
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
- 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
- 2017Interpretation of Neural Networks is Fragilecited by 443
- 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
- 2018On the Robustness of Interpretability Methodscited by 310
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
- 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
- 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
- 2020A Survey on Neural Network Interpretabilitycited by 291
- 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
- 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
- 2017Real Time Image Saliency for Black Box Classifierscited by 246
- 2019Explanations can be manipulated and geometry is to blamecited by 215
- 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
- 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
- 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
- 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
- 2021Towards Robust and Reliable Algorithmic Recoursecited by 101
- 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 100
- 2018Model Agnostic Supervised Local Explanationscited by 83
- 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
- 2020On quantitative aspects of model interpretabilitycited by 71
- 2021Do Input Gradients Highlight Discriminative Features?cited by 52
- 2020Robust and Stable Black Box Explanationscited by 47
- 2020Smoothed Geometry for Robust Attributioncited by 38
- 2020OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithmscited by 30
- 2020How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networkscited by 27
- 2020Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoringcited by 26
- 2020A simple defense against adversarial attacks on heatmap explanationscited by 23
- 2022What Makes a Good Explanation?: A Harmonized View of Properties of Explanationscited by 21
- 2023Explanations of Black-Box Models based on Directional Feature Interactionscited by 15
- 2022s-LIME: Reconciling Locality and Fidelity in Linear Explanationscited by 8
- 2022Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functionscited by 6
- 2022Boundary-Aware Uncertainty for Feature Attribution Explainerscited by 6
- 2023SmoothHess: ReLU Network Feature Interactions via Stein's Lemmacited by 5
- 2024Guided Game Level Repair via Explainable AIcited by 2
- 2024Controllable Game Level Generation: Assessing the Effect of Negative Examples in GAN Modelscited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.