paper-with-me

Papers

HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

2023-04-04 · Lu Chen, Siyu Lou, Keyan Zhang, Jin Huang, Quanshi Zhang

The Shapley value is widely regarded as a trustworthy attribution metric. However, when people use Shapley values to explain the attribution of input variables of a deep neural network (DNN), it usually requires a very high computational cost to approximate relatively accurate Shapley values in real-world applications. Therefore, we propose a novel network architecture, the HarsanyiNet, which makes inferences on the input sample and simultaneously computes the exact Shapley values of the input variables in a single forward propagation. The HarsanyiNet is designed on the theoretical foundation that the Shapley value can be reformulated as the redistribution of Harsanyi interactions encoded by the network.

📄 PDF Abstract BibTeX arXiv:2304.01811

Code (1)

csluchen/harsanyinet 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Exactly Computing do-Shapley Values

2026-02-06 · R. Teal Witter, Álvaro Parafita, Tomas Garriga, Maximilian Muschalik 외 arxiv

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifyi…

Accurate Shapley Values for explaining tree-based models

2021-06-07 · Salim I. Amoukou, Nicolas J-B. Brunel, Tangi Salaün

Shapley Values (SV) are widely used in explainable AI, but their estimation and interpretation can be challenging, leading to inaccurate inferences and explanations. As a starting point, we remind an invariance principle…

Efficient Shapley Values Estimation by Amortization for Text Classification

2023-05-31 · Chenghao Yang, Fan Yin, He He, Kai-Wei Chang 외

Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values …

Classificationtext-classificationText Classification

Fast Shapley Value Estimation: A Unified Approach

2023-11-02 · Borui Zhang, Baotong Tian, Wenzhao Zheng, Jie zhou 외

Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values enco…

Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

2020-11-03 · NeurIPS 2020 12 · Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, Tom Claassen

Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baselin…

AttributeExplainable artificial intelligence