From Shapley Values to Generalized Additive Models and back

• URL: http://arxiv.org/abs/2209.04012v1
• Date: Thu, 8 Sep 2022 19:37:06 GMT
• Title: From Shapley Values to Generalized Additive Models and back
• Authors: Sebastian Bordt, Ulrike von Luxburg
• Abstract summary: We introduce $n$-Shapley Values, a natural extension of Shapley Values that explain individual predictions with interaction terms up to order $n$. From the Shapley-GAM, we can compute Shapley Values of arbitrary order, which gives precise insights into the limitations of these explanations. At the technical end, we show that there is a one-to-one correspondence between different ways to choose the value function and different functional decompositions of the original function.
• Score: 16.665883787432858
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. In this work, offer a novel perspective on Shapley Values, a prominent post-hoc explanation technique, and show that it is strongly connected with Glassbox-GAMs, a popular class of interpretable models. We introduce $n$-Shapley Values, a natural extension of Shapley Values that explain individual predictions with interaction terms up to order $n$. As $n$ increases, the $n$-Shapley Values converge towards the Shapley-GAM, a uniquely determined decomposition of the original function. From the Shapley-GAM, we can compute Shapley Values of arbitrary order, which gives precise insights into the limitations of these explanations. We then show that Shapley Values recover generalized additive models of order $n$, assuming that we allow for interaction terms up to order $n$ in the explanations. This implies that the original Shapley Values recover Glassbox-GAMs. At the technical end, we show that there is a one-to-one correspondence between different ways to choose the value function and different functional decompositions of the original function. This provides a novel perspective on the question of how to choose the value function. We also present an empirical analysis of the degree of variable interaction that is present in various standard classifiers, and discuss the implications of our results for algorithmic explanations. A python package to compute $n$-Shapley Values and replicate the results in this paper is available at \url{https://github.com/tml-tuebingen/nshap}.

Related papers

• Transforming and Combining Rewards for Aligning Large Language Models [69.44634017612798]
  A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We use a log-sigmoid function to transform rewards learned from Bradley-Terry preference models. Experiments aligning language models to be both helpful and harmless using RLHF show substantial improvements over the baseline (non-transformed) approach.
  arXiv  Detail & Related papers  (2024-02-01T16:39:28Z)
• Fast Shapley Value Estimation: A Unified Approach [71.92014859992263]
  We propose a straightforward and efficient Shapley estimator, SimSHAP, by eliminating redundant techniques. In our analysis of existing approaches, we observe that estimators can be unified as a linear transformation of randomly summed values from feature subsets. Our experiments validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
  arXiv  Detail & Related papers  (2023-11-02T06:09:24Z)
• Explaining the Model and Feature Dependencies by Decomposition of the Shapley Value [3.0655581300025996]
  Shapley values have become one of the go-to methods to explain complex models to end-users. One downside is that they always require outputs of the model when some features are missing. This however introduces a non-trivial choice: do we condition on the unknown features or not? We propose a new algorithmic approach to combine both explanations, removing the burden of choice and enhancing the explanatory power of Shapley values.
  arXiv  Detail & Related papers  (2023-06-19T12:20:23Z)
• Efficient Shapley Values Estimation by Amortization for Text Classification [66.7725354593271]
  We develop an amortized model that directly predicts each input feature's Shapley Value without additional model evaluations. Experimental results on two text classification datasets demonstrate that our amortized model estimates Shapley Values accurately with up to 60 times speedup.
  arXiv  Detail & Related papers  (2023-05-31T16:19:13Z)
• Exact Shapley Values for Local and Model-True Explanations of Decision Tree Ensembles [0.0]
  We consider the application of Shapley values for explaining decision tree ensembles. We present a novel approach to Shapley value-based feature attribution that can be applied to random forests and boosted decision trees.
  arXiv  Detail & Related papers  (2021-12-16T20:16:02Z)
• Is Shapley Explanation for a model unique? [0.0]
  We explore the relationship between the distribution of a feature and its Shapley value. Our assessment is that Shapley value for particular feature not only depends on its expected mean but on other moments as well such as variance. It varies with model outcome (Probability/Log-odds/binary decision such as accept vs reject) and hence model application.
  arXiv  Detail & Related papers  (2021-11-23T15:31:46Z)
• groupShapley: Efficient prediction explanation with Shapley values for feature groups [2.320417845168326]
  Shapley values has established itself as one of the most appropriate and theoretically sound frameworks for explaining predictions from machine learning models. The main drawback with Shapley values is that its computational complexity grows exponentially in the number of input features. The present paper introduces groupShapley: a conceptually simple approach for dealing with the aforementioned bottlenecks.
  arXiv  Detail & Related papers  (2021-06-23T08:16:14Z)
• Fast Hierarchical Games for Image Explanations [78.16853337149871]
  We present a model-agnostic explanation method for image classification based on a hierarchical extension of Shapley coefficients. Unlike other Shapley-based explanation methods, h-Shap is scalable and can be computed without the need of approximation. We compare our hierarchical approach with popular Shapley-based and non-Shapley-based methods on a synthetic dataset, a medical imaging scenario, and a general computer vision problem.
  arXiv  Detail & Related papers  (2021-04-13T13:11:02Z)
• On the Adversarial Robustness of LASSO Based Feature Selection [72.54211869067979]
  In the considered model, there is a malicious adversary who can observe the whole dataset, and then will carefully modify the response values or the feature matrix. We formulate the modification strategy of the adversary as a bi-level optimization problem. Numerical examples with synthetic and real data illustrate that our method is efficient and effective.
  arXiv  Detail & Related papers  (2020-10-20T05:51:26Z)
• Predictive and Causal Implications of using Shapley Value for Model Interpretation [6.744385328015561]
  We established the relationship between Shapley value and conditional independence, a key concept in both predictive and causal modeling. Our results indicate that, eliminating a variable with high Shapley value from a model do not necessarily impair predictive performance. More importantly, Shapley value of a variable do not reflect their causal relationship with the target of interest.
  arXiv  Detail & Related papers  (2020-08-12T01:08:08Z)
• Towards Efficient Data Valuation Based on the Shapley Value [65.4167993220998]
  We study the problem of data valuation by utilizing the Shapley value. The Shapley value defines a unique payoff scheme that satisfies many desiderata for the notion of data value. We propose a repertoire of efficient algorithms for approximating the Shapley value.
  arXiv  Detail & Related papers  (2019-02-27T00:22:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.