Shapley Sets: Feature Attribution via Recursive Function Decomposition

• URL: http://arxiv.org/abs/2307.01777v1
• Date: Tue, 4 Jul 2023 15:30:09 GMT
• Title: Shapley Sets: Feature Attribution via Recursive Function Decomposition
• Authors: Torty Sivill and Peter Flach
• Abstract summary: We propose an alternative attribution approach, Shapley Sets, which awards value to sets of features. Shapley Sets decomposes the underlying model into non-separable variable groups. We show theoretically and experimentally how Shapley Sets avoids pitfalls associated with Shapley value based alternatives.
• Score: 6.85316573653194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their ubiquitous use, Shapley value feature attributions can be misleading due to feature interaction in both model and data. We propose an alternative attribution approach, Shapley Sets, which awards value to sets of features. Shapley Sets decomposes the underlying model into non-separable variable groups using a recursive function decomposition algorithm with log linear complexity in the number of variables. Shapley Sets attributes to each non-separable variable group their combined value for a particular prediction. We show that Shapley Sets is equivalent to the Shapley value over the transformed feature set and thus benefits from the same axioms of fairness. Shapley Sets is value function agnostic and we show theoretically and experimentally how Shapley Sets avoids pitfalls associated with Shapley value based alternatives and are particularly advantageous for data types with complex dependency structure.

Related papers

• Group Shapley Value and Counterfactual Simulations in a Structural Model [12.343981093497332]
  We propose a variant of the Shapley value, the group Shapley value, to interpret counterfactual simulations in structural economic models. Our framework compares two sets of parameters, partitioned into multiple groups, and applying group Shapley value decomposition yields unique additive contributions to the changes between these sets.
  arXiv  Detail & Related papers  (2024-10-09T13:38:59Z)
• 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)
• 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)
• WeightedSHAP: analyzing and improving Shapley based feature attributions [17.340091573913316]
  Shapley value is a popular approach for measuring the influence of individual features. We propose WeightedSHAP, which generalizes the Shapley value and learns which marginal contributions to focus directly from data. On several real-world datasets, we demonstrate that the influential features identified by WeightedSHAP are better able to recapitulate the model's predictions.
  arXiv  Detail & Related papers  (2022-09-27T14:34:07Z)
• Joint Shapley values: a measure of joint feature importance [6.169364905804678]
  We introduce joint Shapley values, which directly extend the Shapley axioms. Joint Shapley values measure a set of features' average effect on a model's prediction. Results for games show that joint Shapley values present different insights from existing interaction indices.
  arXiv  Detail & Related papers  (2021-07-23T17:22:37Z)
• 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)
• Bilinear Classes: A Structural Framework for Provable Generalization in RL [119.42509700822484]
  Bilinear Classes is a new structural framework which permits generalization in reinforcement learning. The framework incorporates nearly all existing models in which a sample complexity is achievable. Our main result provides an RL algorithm which has sample complexity for Bilinear Classes.
  arXiv  Detail & Related papers  (2021-03-19T16:34:20Z)
• Multicollinearity Correction and Combined Feature Effect in Shapley Values [0.0]
  Shapley values represent the importance of a feature for a particular row. We present a unified framework to calculate Shapley values with correlated features.
  arXiv  Detail & Related papers  (2020-11-03T12:28:42Z)
• Infinite Feature Selection: A Graph-based Feature Filtering Approach [78.63188057505012]
  We propose a filtering feature selection framework that considers subsets of features as paths in a graph. Going to infinite allows to constrain the computational complexity of the selection process. We show that Inf-FS behaves better in almost any situation, that is, when the number of features to keep are fixed a priori.
  arXiv  Detail & Related papers  (2020-06-15T07:20:40Z)
• Invariant Feature Coding using Tensor Product Representation [75.62232699377877]
  We prove that the group-invariant feature vector contains sufficient discriminative information when learning a linear classifier. A novel feature model that explicitly consider group action is proposed for principal component analysis and k-means clustering.
  arXiv  Detail & Related papers  (2019-06-05T07:15:17Z)
• 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.