Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
Explore this paper's citation graph
Summary
To benchmark the evaluation in IML, this article rigorously defines the problem of evaluating explanations, and systematically review the existing efforts from state-of-the-arts, and summarizes three general aspects of explanation with formal definitions.
- Type
- preprint
- Published
- 2019-07-16
- Cited by
- 81
- References
- 84
- Access
- Open access
- OpenAlex
- https://openalex.org/W2956993847
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:196831873
Keywords
Generalizability theory, Benchmark (surveying), Computer science, Fidelity, Common ground
References
- Interpreting Deep Visual Representations via Network Dissection
- Distilling the Knowledge in a Neural Network
- Fully convolutional networks for semantic segmentation
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
- An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression
- Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
- Generalized Linear Models
- Principles of Explanatory Debugging to Personalize Interactive Machine Learning
- How should I explain? A comparison of different explanation types for recommender systems
- Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
- A survey of decision tree classifier methodology
- Deep Neural Networks for Object Detection
- Explaining Recommendations: Satisfaction vs. Promotion
- Tell me more?: the effects of mental model soundness on personalizing an intelligent agent
- Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
- The Role of Explanations on Trust and Reliance in Clinical Decision Support Systems
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier
- Learning Deep Features for Discriminative Localization
- User Trust in Intelligent Systems: A Journey Over Time
- Interpretable Decision Sets: A Joint Framework for Description and Prediction
Cited by
- Learning Credible Deep Neural Networks with Rationale Regularization
- On Concept-Based Explanations in Deep Neural Networks
- Towards a Unified Evaluation of Explanation Methods without Ground Truth
- A Taxonomy for Human Subject Evaluation of Black-Box Explanations in XAI
- Explainable Deep Learning: A Field Guide for the Uninitiated
- Evaluating and Aggregating Feature-based Model Explanations
- Explainable Matrix - Visualization for Global and Local Interpretability of Random Forest Classification Ensembles
- Causal Interpretability for Machine Learning - Problems, Methods and Evaluation
- Explaining Neural Networks by Decoding Layer Activations
- Explainable Rumor Detection using Inter and Intra-feature Attention Networks
- Utilizing black-box visualization tools to interpret non-parametric real-time risk assessment models
- Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability
- What Do You See?: Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors
- DeepConsensus: Consensus-based Interpretable Deep Neural Networks with Application to Mortality Prediction
- Explainable Deep Relational Networks for Predicting Compound–Protein Affinities and Contacts
- Data Representing Ground-Truth Explanations to Evaluate XAI Methods
- A Review on Explainability in Multimodal Deep Neural Nets
- Multimodal Hierarchical Attention Neural Network: Looking for Candidates Behaviour Which Impact Recruiter's Decision
- Few-Shot Self-Rationalization with Natural Language Prompts
- A Review of Interpretable ML in Healthcare: Taxonomy, Applications, Challenges, and Future Directions
Related papers
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier
- Towards A Rigorous Science of Interpretable Machine Learning
- Sanity Checks for Saliency Maps
- Understanding Black-box Predictions via Influence Functions
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
- A systematic review and taxonomy of explanations in decision support and recommender systems