SHAP (SHapley Additive exPlanation) values are one of the leading tools for interpreting machine learning models, with strong theoretical guarantees (consistency, local accuracy) and a wide availability of implementations and use cases. Even though computing SHAP values takes exponential time in general, TreeSHAP takes polynomial time on tree-based models. While the speedup is significant, TreeSHAP can still dominate the computation time of industry-level machine learning solutions on datasets with millions or more entries, causing delays in post-hoc model diagnosis and interpretation service. In this paper we present two new algorithms, Fast TreeSHAP v1 and v2, designed to improve the computational efficiency of TreeSHAP for large datasets. We empirically find that Fast TreeSHAP v1 is 1.5x faster than TreeSHAP while keeping the memory cost unchanged. Similarly, Fast TreeSHAP v2 is 2.5x faster than TreeSHAP, at the cost of a slightly higher memory usage, thanks to the pre-computation of expensive TreeSHAP steps. We also show that Fast TreeSHAP v2 is well-suited for multi-time model interpretations, resulting in as high as 3x faster explanation of newly incoming samples.
Fast Estimation of Partial Dependence Functions using Trees
University of Copenhagen（哥本哈根大学）；University of Bremen（不来梅大学）；Leibniz Institute for Prevention Research and Epidemiology - BIPS（莱布尼茨预防研究与流行病学研究所 - BIPS）
TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees
Department of Computer Science, National University of Singapore, Republic of Singapore（新加坡国立大学计算机科学系）；School of Computer Science, University of Waterloo, Canada（滑铁卢大学计算机科学学院）；Vector Institute, Canada（加拿大向量研究所）
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Warsaw（华沙大学）；Warsaw University of Technology（华沙理工大学）；Bielefeld University（比勒费尔德大学）；CITEC（认知交互技术中心）；Paderborn University（帕德博恩大学）
Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks
Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；University of California Santa Cruz（加州大学圣克鲁兹分校）；California Institute of Technology（加州理工学院）；Georgia Institute of Technology（佐治亚理工学院）；NVIDIA Corporation（英伟达公司）；University of California, Riverside（加州大学河滨分校）；Institute of Astronomy and Astrophysics, Academia Sinica（中央研究院天文及天文物理研究所）；University of Bern（伯尔尼大学）
Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone
Sandia National Laboratories（桑迪亚国家实验室）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；University of California, Berkeley（加州大学伯克利分校）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
