paper-with-me

Papers

Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf

2021-08-09 · Adam Karczmarz, Anish Mukherjee, Piotr Sankowski, Piotr Wygocki

Shapley values are one of the main tools used to explain predictions of tree ensemble models. The main alternative to Shapley values are Banzhaf values that have not been understood equally well. In this paper we make a step towards filling this gap, providing both experimental and theoretical comparison of these model explanation methods. Surprisingly, we show that Banzhaf values offer several advantages over Shapley values while providing essentially the same explanations. We verify that Banzhaf values: (1) have a more intuitive interpretation, (2) allow for more efficient algorithms, and (3) are much more numerically robust. We provide an experimental evaluation of these theses. In particular, we show that on real world instances. Additionally, from a theoretical perspective we provide new and improved algorithm computing the same Shapley value based explanations as the algorithm of Lundberg et al. [Nat. Mach. Intell. 2020]. Our algorithm runs in $O(TLD+n)$ time, whereas the previous algorithm had $O(TLD^2+n)$ running time bound. Here, $T$ is the number of trees, $L$ is the maximum number of leaves in a tree, and $D$ denotes the maximum depth of a tree in the ensemble. Using the computational techniques developed for Shapley values we deliver an optimal $O(TL+n)$ time algorithm for computing Banzhaf values based explanations. In our experiments these algorithms give running times smaller even by an order of magnitude.

📄 PDF Abstract BibTeX arXiv:2108.04126

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance

Similar Papers 제목 키워드 기반

On Explainability of Graph Neural Networks via Subgraph Explorations

2021-02-09 · Hao Yuan, Haiyang Yu, Jie Wang, Kang Li 외

We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges…

Inferring feature importance with uncertainties in high-dimensional data

2021-09-02 · Pål Vegard Johnsen, Inga Strümke, Signe Riemer-Sørensen, Andrew Thomas DeWan 외

Estimating feature importance is a significant aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating p…

Feature ImportanceVocal Bursts Intensity Prediction

Shapley Computations Using Surrogate Model-Based Trees

2022-07-11 · Zhipu Zhou, Jie Chen, Linwei Hu

Shapley-related techniques have gained attention as both global and local interpretation tools because of their desirable properties. However, their computation using conditional expectations is computationally expensive…

model

From global to local MDI variable importances for random forests and when they are Shapley values

2021-11-03 · NeurIPS 2021 12 · Antonio Sutera, Gilles Louppe, Van Anh Huynh-Thu, Louis Wehenkel 외

Random forests have been widely used for their ability to provide so-called importance measures, which give insight at a global (per dataset) level on the relevance of input variables to predict a certain output. On the …

Consistent feature attribution for tree ensembles

2017-06-19 · Scott M. Lundberg, Su-In Lee

Note that a newer expanded version of this paper is now available at: arXiv:1802.03888 It is critical in many applications to understand what features are important for a model, and why individual predictions were made…

ClusteringFeature Importance