From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process
Not on the map. Why?
Abstract (arXiv)
Explainable AI (XAI) is a necessity in safety-critical systems such as in clinical diagnostics due to a high risk for fatal decisions. Currently, however, XAI resembles a loose collection of methods rather than a well-defined process. In this work, we elaborate on conceptual similarities between the largest subgroup of XAI, interpretable machine learning (IML), and classical statistics. Based on these similarities, we present a formalization of IML along the lines of a statistical process. Adopting this statistical view allows us to interpret machine learning models and IML methods as sophisticated statistical tools. Based on this interpretation, we infer three key questions, which we identify as crucial for the success and adoption of IML in safety-critical settings. By formulating these questions, we further aim to spark a discussion about what distinguishes IML from classical statistics and what our perspective implies for the future of the field.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 75 references that are in the map. First posted on arXiv 11 Jul 2022.
Builds on
33 of 75 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2014Striving for Simplicity: The All Convolutional Netcited by 990
- 2018Disentangling by Factorisingcited by 616
21 more
- 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
- 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
- 2019Causality for Machine Learningcited by 243
- 2021Towards Causal Representation Learningcited by 209
- 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
- 2020Restricting the Flow: Information Bottlenecks for Attributioncited by 110
- 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
- 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
- 2020Aligning Faithful Interpretations with their Social Attributioncited by 79
- 2020Model Interpretability through the Lens of Computational Complexitycited by 75
- 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 70
- 2018A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizationscited by 60
- 2021Common Limitations of Image Processing Metrics: A Picture Storycited by 59
- 2020Interpretability and Explainability: A Machine Learning Zoo Mini-tourcited by 55
- 2020dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Pythoncited by 40
- 2017Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classificationcited by 39
- 2019Practical Solutions for Machine Learning Safety in Autonomous Vehiclescited by 15
- 2020Survey of XAI in digital pathologycited by 14
- 2017Towards the Augmented Pathologist: Challenges of Explainable-AI in Digital Pathologycited by 13
- 2019Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictionscited by 1
Built on by
Not cited yet.