Interpretable Machine Learning: Moving From Mythos to Diagnostics
arXiv:2103.06254
Abstract
Despite increasing interest in the field of Interpretable Machine Learning (IML), a significant gap persists between the technical objectives targeted by researchers' methods and the high-level goals of consumers' use cases. In this work, we synthesize foundational work on IML methods and evaluation into an actionable taxonomy. This taxonomy serves as a tool to conceptualize the gap between researchers and consumers, illustrated by the lack of connections between its methods and use cases components. It also provides the foundation from which we describe a three-step workflow to better enable researchers and consumers to work together to discover what types of methods are useful for what use cases. Eventually, by building on the results generated from this workflow, a more complete version of the taxonomy will increasingly allow consumers to find relevant methods for their target use cases and researchers to identify applicable use cases for their proposed methods.
arXiv commentPresented at ICML HILL Workshop 2021
References in corpus (24)
- Towards A Rigorous Science of Interpretable Machine Learning
- Axiomatic Attribution for Deep Networks
- Interpretable machine learning: definitions, methods, and applications
- Understanding Black-box Predictions via Influence Functions
- Sanity Checks for Saliency Maps
- Actionable Recourse in Linear Classification
- A Benchmark for Interpretability Methods in Deep Neural Networks
- One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
- Distilling a Neural Network Into a Soft Decision Tree
- The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
- Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
- Learning Model-Agnostic Counterfactual Explanations for Tabular Data
- Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
- Model Agnostic Supervised Local Explanations
- Neural Additive Models: Interpretable Machine Learning with Neural Nets
- On the Robustness of Interpretability Methods
- Representer Point Selection for Explaining Deep Neural Networks
- Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions
- Contextual Explanation Networks
- Regularizing Black-box Models for Improved Interpretability
- Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
- Issues with post-hoc counterfactual explanations: a discussion
- Explaining Groups of Points in Low-Dimensional Representations
- A Learning Theoretic Perspective on Local Explainability