Keith Richards Subject: Christianity is the answer NTTP-Posting-Host: x.x.com I think Christianity is the one true religion. If you’d like to know more, send me a note 11
interpretable by humans - May not be globally faithful… 2. Locally approximate global (blackbox) model - Simple model is globally bad, but locally good Line, shallow decision tree, sparse features, … Locally-faithful simple decision boundary ➔ Good explanation for prediction 15
to search over Faithfulness of Explanation Is the explanation faithful to the model in context of x Interpretability Is the explanation simple enough to read? 16
predict labels for each sample 3. Weigh samples according to distance to xi 4. Learn new simple model on weighted samples 5. Use simple model to explain Sparse Linear Explanations 17
is the answer NTTP-Posting-Host: x.x.com I think Christianity is the one true religion. If you’d like to know more, send me a note After looking at the explanation, we shouldn’t trust the model! 24
constraints on individual features Quality of Constraints Whether all instances that satisfy the constraints e have the same prediction Interpretability Are the set of constraints small? Find a set of constraints so that any other change to the input does not change the prediction 29
possible programs/functions on x Quality of Program Does the function e on instances similar to x perform similar to the model Interpretability Is the program short? There are so many choices for interpretable models: Rules, decision trees, decision sets, falling lists, sparse linear models, etc. Why decide between them, search over ALL possible “programs”! 33
be applied on future models as well LIME Local, Interpretable Model-Agnostic Explanations Linear explanations: useful for complex text and image classifiers Prediction Invariant explanations: a more precise definition “Programs” as explanations: generalizes over any representations 35
for complex text and image classifiers Prediction Invariant explanations: a more precise definition “Programs” as explanations: generalizes over any representations www.sameersingh.org github.com/marcotcr/lime