Model Interpretability with SHAP and LIME
Chapter 1: Foundations of Model Interpretability
Why Explain Model Predictions?
Interpretability vs. Explainability
Taxonomy of Interpretability Methods
Scope of Explanations: Global vs. Local
Challenges in Model Interpretation
Quiz for Chapter 1
Chapter 2: Local Interpretable Model-agnostic Explanations (LIME)
Intuition Behind LIME
How LIME Works: Perturbation and Surrogate Models
Applying LIME to Tabular Data
Applying LIME to Text Data
Interpreting LIME Explanations
LIME Implementation with Python
Limitations and Considerations for LIME
Hands-on Practical: Generating LIME Explanations
Quiz for Chapter 2
Chapter 3: SHapley Additive exPlanations (SHAP)
Introduction to Shapley Values
SHAP Values: Connecting Shapley to Model Features
Properties of SHAP Values
KernelSHAP: A Model-Agnostic Approach
TreeSHAP: Optimized for Tree-Based Models
Interpreting SHAP Plots: Force Plots
Interpreting SHAP Plots: Summary and Dependence Plots
SHAP Implementation with Python
Hands-on Practical: Calculating SHAP Values
Quiz for Chapter 3
Chapter 4: Comparing and Applying Interpretability Techniques
LIME vs. SHAP: Differences
LIME vs. SHAP: Strengths and Weaknesses
Choosing Between LIME and SHAP
Interpreting Explanations for Regression Models
Interpreting Explanations for Classification Models
Integrating Interpretability into the ML Workflow
Common Gotchas and Considerations
Practice: Comparing LIME and SHAP Outputs
Quiz for Chapter 4
Scope of Explanations: Global vs. Local
Was this section helpful?
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier, Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin, 2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (ACM) DOI: 10.1145/2939672.2939778 - Introduces LIME, a widely used technique for local model-agnostic explanations.
- A Unified Approach to Interpreting Model Predictions, Scott M. Lundberg, Su-In Lee, 2017 Advances in Neural Information Processing Systems, Vol. 30 (Curran Associates, Inc.) - Presents SHAP, a method that unifies various explanation techniques and provides both local and aggregated global explanations.
- Interpretable Machine Learning. A Guide for Making Black Box Models Explainable., Christoph Molnar, 2022 (Lulu.com) - A comprehensive open-source book covering various model interpretability methods, including global techniques like PDP, ALE, and local techniques like LIME and SHAP.
- Visualizing the Effects of Predictor Variables in Black Box Models, Daniel W. Apley, Jingyu Zhu, 2020 Journal of the Royal Statistical Society Series B: Statistical Methodology, Vol. 82 (Wiley) DOI: 10.1111/rssb.12377 - Introduces Accumulated Local Effects (ALE) plots, an effective and unbiased method for global feature effect visualization.