Questions tagged [lime]
Questions related to the Locally Interpretable Model-Agnostic Explanations (LIME) method of explaining black-box machine learning models.
30
questions
1
vote
0
answers
25
views
Using LIME to interpret model predictions in R
I am running models, and I am learning how to use LIME to explain the models. I trained a random forest, on data that has 988 rows and 5000 columns. However, I am getting an error which says ...
- 13
0
votes
1
answer
18
views
How to use LIME to explain the best performing model?
I am trying to perform model explainability for the best performing model using LIME for a classification problem. The y variable is whether a tumour is malignant or benign. Same question as (https://...
- 13
1
vote
0
answers
27
views
Feature selection based on production data
I have a classifer (one/zero labels) that was trained and hypertuned by the book. When the model was ready, I applied it to the production data: real-time and unlabeled.
After a short period (a few ...
- 105
1
vote
0
answers
81
views
Appropriateness of using SHAP values to evaluate a model
I am a deep learning researcher that would like to use SHAP values to assess the relative importance of input features on the model's final score. Colleagues of mine have taken issue with the method ...
- 21
1
vote
0
answers
92
views
interpret lime results
What is the meaning of the values of the "blue" features in the lime output? I understand that they influence the lime black-box model to classify an observation as 0 label, but what is the ...
- 105
0
votes
0
answers
108
views
Does lime score matter for continuous variable discretization?
I am using a random forest classifier for binary classification with 977 records and class proportion of 77:23.
I am using Lime explainer to explain the predictions made by the model.
However, I see ...
- 2,894
1
vote
0
answers
96
views
How to handle inconsistency in ML explanations?
I found out that we have different solutions like below to explain the ML predictions
a) LIME
b) SHAP
Despite using all these approaches, I see that all of them work for certain data points and not ...
- 2,894
2
votes
0
answers
276
views
Lime predictions - Interpretation
I am working on a binary classification using random forest and explanation using LIME. I already referred the posts here, here and here.
I have the feature contribution info from LIME like as shown ...
- 2,894
1
vote
1
answer
308
views
Understanding the output of LIME - How is the contribution of features related to the predicted output?
How is the contribution of features extract from explaining a regression model with LIME locally related to the predicted output of the surrogate model?
I thought that LIME is additive (some blog post ...
- 543
5
votes
1
answer
830
views
Is there any reason to use LIME now that shap is available?
The context: explaining a binary classifier XGBoost model.
If we say that we are limited to the LIME and Shapley Additive Explanation aka "shap" package, is there any reason to use LIME? My ...
- 453
0
votes
0
answers
328
views
Using LIME without intercept term?
I'm playing with LIME to explain the prediction of a machine learning model.
LIME trains a (locally weighted) linear surrogate model around a point of interest. The weights of that surrogate model are ...
- 1,011
2
votes
2
answers
147
views
Choosing Interpretable Models model vs choosing black box model and explain it with shap/lime
I analyse a dateset of article. The articles are labeled as popular or not popular and off course each article has features like: article section, article writer and etc.
I don't want to predict if a ...
- 105
1
vote
0
answers
208
views
Using SHAP or LIME to explain new predictions?
I've previously used SHAP and LIME to explain predictions from a training set, i.e. I have the actual target value.
Is it possible to do the same to explain new predictions, i.e. I don't have the ...
- 11
1
vote
0
answers
50
views
Why LIME does not show the attribution for each features
For the second(central) numbers, why all the features do not attribute to the prediction probabilities? The data is credit default data, here "0" means no default credit, "1" means ...
- 11
2
votes
1
answer
327
views
LIME Shows Very High Probability Score, But Breakdown Has All Negative Factors
I'm using LIME to break down the observation for each row and am taking a look at the positive and negative factors that contribute to the probability outputted.
I filtered my dataset down to only ...
- 83
5
votes
2
answers
273
views
LIME Analysis Linear Model
I am looking at explaining a single prediction for a linear model:
Y = F(X) = x0 + a1x1 + a2x2 + ... anxn i.e. F: X -> Y
i.e. given a single instance z in X, ...
- 997
3
votes
1
answer
2k
views
Using Lime on a binary classification neural network
I would like to use Lime to interpret a neural network model.
For the sake of this question, I made a simple Dense model using this dataset:
https://raw.githubusercontent.com/jbrownlee/Datasets/...
- 53
5
votes
2
answers
1k
views
Reasons that LIME and SHAP might not agree with intuition
I'm leveraging the Python packages lime and shap to explain single (test-set) predictions that a basic, trained model is making on new, tabular data. WLOG, the explanations generated by both methods ...
- 173
1
vote
0
answers
237
views
Curious on using black box model interpreters (LIME, SHAP, etc) for production models
So, I'm wondering how many of you have been in a similar situation:
We have a XGBoost classifier in production that is performing really well. As an enhancement, I want to add an explainer to provide ...
- 287
1
vote
0
answers
294
views
interpretation of plot_features output in LIME- supports vs contradicts output doesn't match the sign of feature_value * feature_weight [closed]
I've created a GBM model explanation using LIME and have used plot_features to plot the results. I'm confused by the mismatch between the output of the plot, in terms of Supporting and Contradicting ...
- 111
0
votes
0
answers
87
views
Scaled and Unscaled features are giving different feature importances when using LIME
Now, based on my understanding, feature scaling should have no impact on my model results due to the fact that XGBoost isn't sensitive to monotonic transformations. Ref
My concern is the model ...
- 287
3
votes
1
answer
44
views
Interpreting/Quantifying what is causing changes in ML model predictions week over week Ask
We are currently predicting an online students likelihood of completing a class each week. We use a lot of demographic information (which is constant throughout the class), as well as a small number ...
- 1,199
2
votes
0
answers
1k
views
What are the differences between LIME and SHAP as model interpretation techniques?
Model interpretation has been an important area of study nowadays and because of that some different techniques have risen to help on this task. Maybe the two most famous ones are LIME and SHAP.
How ...
36
votes
1
answer
13k
views
Comparison between SHAP (Shapley Additive Explanation) and LIME (Local Interpretable Model-Agnostic Explanations)
I am reading up about two popular post hoc model interpretability techniques: LIME and SHAP
I am having trouble understanding the key difference in these two techniques.
To quote Scott Lundberg, ...
- 471
2
votes
1
answer
555
views
Understanding functioning of LIME(Local Interpretable Model-agnostic Explanations)
Following are the steps that occur in LIME's algorithm
https://cran.r-project.org/web/packages/lime/vignettes/Understanding_lime.html
I have been trying to read and understand why this process is ...
- 315
1
vote
1
answer
2k
views
Why LIME does not show prediction probability for the other class?
On the picture above you can see prediction probabilities. In this case it shows 100% poisonous. However, on next two figures it shows that there is actually small probability of other class (with ...
- 15
0
votes
0
answers
74
views
How does LIME compares with Mutual Information?
So, I was wondering how LIME's linear model approach compares with other explanation metrics, in special, with Mutual Information?
For those unfamiliar with how LIME works:
Choose the instance you ...
- 101
2
votes
1
answer
1k
views
H2o interpretability - LIME
I have trained a model to predict heart attacks using random forest algorithm using H2O.
I have good performance in cross validation.
Now, I want to give more interpretation to the predictions in a ...
- 21
4
votes
1
answer
2k
views
How to interpret probabilities together with output from R lime package?
My question is related to this one: LIME explanation confusion. But since it does not have a reproducible example or an answer, I am asking here with an example.
I have a dataset with unbalanced ...
- 225
1
vote
1
answer
1k
views
LIME explanation confusion [closed]
I am working in R creating a GBM model using H2O and trying to use LIME to look at some local explanations to get a feel for what the model is doing. It's a binary classifier and I'm specifying 8 for ...
- 1,628