paper-with-me

홈 › Papers

Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae

2025-09-12 · Stav Armoni-Friedmann, Hana Chockler, David A. Kelly arxiv

Evaluating explainable AI (XAI) approaches is a challenging task in general, due to the subjectivity of explanations. In this paper, we focus on tabular data and the specific use case of AI models predicting the values of Boolean functions. We extend the previous work in this domain by proposing a formal and precise measure of importance of variables based on actual causality, and we evaluate state-of-the-art XAI tools against this measure. We also present a novel XAI tool B-ReX, based on the existing tool ReX, and demonstrate that it is superior to other black-box XAI tools on a large-scale benchmark. Specifically, B-ReX achieves a Jensen-Shannon divergence of 0.072 $\pm$ 0.012 on random 10-valued Boolean formulae

📄 PDF Abstract BibTeX arXiv:2509.09982

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Black-Box Complexity of the Binary Value Function

2019-04-09 · Nina Bulanova, Maxim Buzdalov

The binary value function, or BinVal, has appeared in several studies in theory of evolutionary computation as one of the extreme examples of linear pseudo-Boolean functions. Its unbiased black-box complexity was previou…

Agnostic proper learning of monotone functions: beyond the black-box correction barrier

2023-04-05 · Jane Lange, Arsen Vasilyan

We give the first agnostic, efficient, proper learning algorithm for monotone Boolean functions. Given $2^{\tilde{O}(\sqrt{n}/\varepsilon)}$ uniformly random examples of an unknown function $f:\{\pm 1\}^n \rightarrow \{\…

Diffusion Models for Black-Box Optimization

2023-06-12 · Siddarth Krishnamoorthy, Satvik Mehul Mashkaria, Aditya Grover

The goal of offline black-box optimization (BBO) is to optimize an expensive black-box function using a fixed dataset of function evaluations. Prior works consider forward approaches that learn surrogates to the black-bo…

Denoising

SHAP values via sparse Fourier representation

2024-10-08 · Ali Gorji, Andisheh Amrollahi, Andreas Krause

SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI. We propose an efficient two-stage algorithm for computing SHAP values in both black-…

Learning SMaLL Predictors

2018-03-06 · NeurIPS 2018 12 · Vikas K. Garg, Ofer Dekel, Lin Xiao

We present a new machine learning technique for training small resource-constrained predictors. Our algorithm, the Sparse Multiprototype Linear Learner (SMaLL), is inspired by the classic machine learning problem of lear…

BIG-bench Machine Learning