0% found this document useful (0 votes)
8 views19 pages

Explainable AI

The document discusses the importance of explainable AI, highlighting the need for transparency, trust, and fairness in AI decision-making. It compares two model-agnostic explanation methods, LIME and SHAP, detailing their mechanisms and use cases, with LIME focusing on local interpretability and SHAP providing both local and global insights. The document concludes by recommending LIME for speed and simplicity, while SHAP is preferred for comprehensive interpretability across instances.

Uploaded by

aadi jain
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
8 views19 pages

Explainable AI

The document discusses the importance of explainable AI, highlighting the need for transparency, trust, and fairness in AI decision-making. It compares two model-agnostic explanation methods, LIME and SHAP, detailing their mechanisms and use cases, with LIME focusing on local interpretability and SHAP providing both local and global insights. The document concludes by recommending LIME for speed and simplicity, while SHAP is preferred for comprehensive interpretability across instances.

Uploaded by

aadi jain
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Explainable AI

Author: Rohit Mande


Founder and CEO, [Link]

Website: [Link]
Website: [Link]

Website: [Link]
Index

• Need of explainable AI
• Why feature importance is not enough?
• LIME
• SHAP
• LIME vs SHAP

Website: [Link]

Website: [Link]
Need of Explainable AI

Website: [Link]

Website: [Link]
Need of Explainable AI

 Transparency and Accountability


Understanding how AI models arrive at specific conclusions or predictions is essential for holding systems accountable for their
actions

 Building Trust
When users understand the reasoning behind AI decisions, they are more likely to trust and adopt these technologies

 Mitigating Bias and Fairness Concerns


By providing insights into the features that influence decisions, stakeholders can assess and address potential biases

 Human-AI Collaboration Website: [Link]


When users understand the rationale behind AI suggestions or decisions, they can provide valuable feedback, corrections, or
insights

Website: [Link]
Why feature importance is not enough?

Website: [Link]

Website: [Link]
Why feature importance is not enough?

Disadvantages of global feature importance:


 Global feature importance such as feature importance from LR, random forest, xgboost gives
important features based on the complete training data
 These methods are not able to give feature importance at the instance level i.e., for every single
row
 Global feature importance might not provide consistent explanations for different instances,
leading to difficulties in trust and reliability.

Website: [Link]

Website: [Link]
Model-Agnostic Explanations

Model-Agnostic Explanations:
 These methods can be applied to any machine learning model. They focus on understanding the
behavior of the model without relying on its internal structure.
 Designed to provide local interpretability by explaining the predictions of a model for a specific
instance.
 These methods consider feature interactions by providing locally faithful explanations.

Explainable AI methods:
 LIME
 SHAP Website: [Link]

Website: [Link]
LIME

Website: [Link]

Website: [Link]
LIME

LIME: Local Interpretable Model-agnostic Explanations

LIME is designed to provide insights into individual predictions rather than global model behavior

Image source: LIME research paper

Website: [Link]

Website: [Link]
LIME Steps

 Create the perturbed instances near the instance for


which prediction is to be explained
 Perturbed instances are given to ML model to get the
predicted label
 Perturbed Instances which are closer to the current
instance are given higher weightage
 Linear interpretable model is learned from the weighted
samples, and it provides explanations for a particular
prediction for the instance
Image source: LIME research paper
 Model's coefficients can be inspected and seen as
proxies for local feature importance.
Website: [Link]

Website: [Link]
LIME

 LIME builds Linear Regression Model to create a locally explainable model in case of regression

 LIME builds Logistic Regression Model to create a locally explainable model in case of
classification

 Coefficients of the features can be used for explaining the model for that instance

Website: [Link]

Website: [Link]
SHAP

Website: [Link]

Website: [Link]
SHAP

SHAP: SHapley Additive exPlanations

SHAP can provide local as well as global feature importance

SHAP values are based on cooperative game theory, specifically Shapley values, which fairly
distribute the "payoff" among a group of contributors.

Website: [Link]

Website: [Link]
How SHAP works?

 Generate All Possible Feature Combinations


Enumerate all possible subsets (coalitions) of features, excluding and including each feature
individually. For a dataset with three features (A, B, C), you would generate coalitions like {}, {A}, {B},
{C}, {A, B}, {A, C}, {B, C}, {A, B, C}.

Evaluate Model Predictions for Each Coalition (combination)


For each subset of features, evaluate the model's prediction on the dataset. This includes the empty
coalition {}.

Website: [Link]

Website: [Link]
How SHAP works?

Calculate Marginal Contributions:


For each subset (coalition), calculate the marginal contribution of each feature that is not in the
coalition but is added to it.
Marginal Contribution(i,S) = Model Prediction(S ∪ {i}) − Model Prediction(S)

Average Marginal Contributions:


For each feature, average its marginal contributions over all possible coalitions.
This average reflects the feature's Shapley value, representing its fair contribution to the model's
prediction.
Website: [Link]

Website: [Link]
SHAP Example

Website: [Link]

Website: [Link]
LIME vs SHAP

Website: [Link]

Website: [Link]
LIME vs SHAP

 Go for LIME when Simplicity and Speed Matter


 LIME tends to be computationally faster compared to SHAP, especially when dealing with complex
models or large datasets

 SHAP is well-suited for scenarios where you require both local and global interpretability.
 SHAP values inherently account for interactions between features.
 SHAP values are designed to be consistent across different instances, providing a more stable and
Website:
reliable framework for interpreting [Link]
model predictions across a range of data points.

Website: [Link]
Questions?

Website: [Link]

Website: [Link]

You might also like