Shapley Sets: Feature Attribution via Recursive Function Decomposition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessSimilar Papers 제목 키워드 기반
Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles
While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box mode…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Exact Shapley Attributions in Quadratic-time for FANOVA Gaussian Processes
Shapley values are widely recognized as a principled method for attributing importance to input features in machine learning. However, the exact computation of Shapley values scales exponentially with the number of featu…
Gaussian ProcessesWeightedSHAP: analyzing and improving Shapley based feature attributions
Shapley value is a popular approach for measuring the influence of individual features. While Shapley feature attribution is built upon desiderata from game theory, some of its constraints may be less natural in certain …
Computing Exact Shapley Values in Polynomial Time for Product-Kernel Methods
Kernel methods are widely used in machine learning due to their flexibility and expressive power. However, their black-box nature poses significant challenges to interpretability, limiting their adoption in high-stakes a…
Computational EfficiencyMaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
Generative search engines based on large language models (LLMs) are replacing traditional search, fundamentally changing how information providers are compensated. To sustain this ecosystem, we need fair mechanisms to at…