Kernel Banzhaf: A Fast and Robust Estimator for Banzhaf Values
Banzhaf values offer a simple and interpretable alternative to the widely-used Shapley values. We introduce Kernel Banzhaf, a novel algorithm inspired by KernelSHAP, that leverages an elegant connection between Banzhaf values and linear regression. Through extensive experiments on feature attribution tasks, we demonstrate that Kernel Banzhaf substantially outperforms other algorithms for estimating Banzhaf values in both sample efficiency and robustness to noise. Furthermore, we prove theoretical guarantees on the algorithm's performance, establishing Kernel Banzhaf as a valuable tool for interpretable machine learning.
Code (1)
Tasks
Interpretable Machine LearningSimilar Papers 제목 키워드 기반
Robust Data Valuation with Weighted Banzhaf Values
Data valuation, a principled way to rank the importance of each training datum, has become increasingly important. However, existing value-based approaches (e.g., Shapley) are known to suffer from the stochasticity inher…
Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf
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 …
Feature ImportanceGame-theoretic Counterfactual Explanation for Graph Neural Networks
Graph Neural Networks (GNNs) have been a powerful tool for node classification tasks in complex networks. However, their decision-making processes remain a black-box to users, making it challenging to understand the reas…
counterfactualCounterfactual ExplanationDecision MakingNode ClassificationGoing with the Flow: Approximating Banzhaf Values via Graph Neural Networks
Computing the Banzhaf value in network flow games is fundamental for quantifying agent influence in multi-agent systems, with applications ranging from cybersecurity to infrastructure planning. However, exact computation…
Data Banzhaf: A Robust Data Valuation Framework for Machine Learning
Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data valuation to noisy model performance sc…
Data Valuation