paper-with-me

Papers

groupShapley: Efficient prediction explanation with Shapley values for feature groups

2021-06-23 · Martin Jullum, Annabelle Redelmeier, Kjersti Aas

Shapley values has established itself as one of the most appropriate and theoretically sound frameworks for explaining predictions from complex machine learning models. The popularity of Shapley values in the explanation setting is probably due to its unique theoretical properties. The main drawback with Shapley values, however, is that its computational complexity grows exponentially in the number of input features, making it unfeasible in many real world situations where there could be hundreds or thousands of features. Furthermore, with many (dependent) features, presenting/visualizing and interpreting the computed Shapley values also becomes challenging. The present paper introduces groupShapley: a conceptually simple approach for dealing with the aforementioned bottlenecks. The idea is to group the features, for example by type or dependence, and then compute and present Shapley values for these groups instead of for all individual features. Reducing hundreds or thousands of features to half a dozen or so, makes precise computations practically feasible and the presentation and knowledge extraction greatly simplified. We prove that under certain conditions, groupShapley is equivalent to summing the feature-wise Shapley values within each feature group. Moreover, we provide a simulation study exemplifying the differences when these conditions are not met. We illustrate the usability of the approach in a real world car insurance example, where groupShapley is used to provide simple and intuitive explanations.

📄 PDF Abstract BibTeX arXiv:2106.12228

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Unified Shapley Framework to Explain Prediction Drift

2021-02-15 · Aalok Shanbhag, Avijit Ghosh, Josh Rubin

Predictions are the currency of a machine learning model, and to understand the model's behavior over segments of a dataset, or over time, is an important problem in machine learning research and practice. There currentl…

BIG-bench Machine LearningPrediction

Joint Shapley values: a measure of joint feature importance

2021-07-23 · ICLR 2022 4 · Chris Harris, Richard Pymar, Colin Rowat

The Shapley value is one of the most widely used measures of feature importance partly as it measures a feature's average effect on a model's prediction. We introduce joint Shapley values, which directly extend Shapley's…

Feature Importance

Explaining individual predictions when features are dependent: More accurate approximations to Shapley values

2019-03-25 · Kjersti Aas, Martin Jullum, Anders Løland

Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanat…

BIG-bench Machine Learning

Shapley Residuals: Quantifying the limits of the Shapley value for explanations

2021-12-01 · NeurIPS 2021 12 · Indra Kumar, Carlos Scheidegger, Suresh Venkatasubramanian, Sorelle Friedler

Popular feature importance techniques compute additive approximations to nonlinear models by first defining a cooperative game describing the value of different subsets of the model's features, then calculating the resul…

AttributeFeature Importance

Shapley values for cluster importance: How clusters of the training data affect a prediction

2020-12-07 · Andreas Brandsæter, Ingrid K. Glad

This paper proposes a novel approach to explain the predictions made by data-driven methods. Since such predictions rely heavily on the data used for training, explanations that convey information about how the training …

Explainable artificial intelligenceFeature Importance