用可学习函数直接预测模型输出，解释更准且推理更快。
Prediction via Shapley Value Regression
- 用柯尔莫哥洛夫-阿诺德网络学习生成沙普利值
- 在表格数据上性能媲美顶尖算法，图像解释更准确
- 适合需要快速解释的部署场景，提升可解释性效率
沙普利值具有理论完备的可解释性属性，但传统后验计算会增加推理开销。为此，本文提出一种新方法ViaSHAP，通过学习一个函数直接生成沙普利值，并基于求和得到预测结果。研究探索了两种实现方式：一种基于通用逼近定理，另一种基于柯尔莫哥洛夫-阿诺德表示定理。大规模实证结果显示，采用柯尔莫哥洛夫-阿诺德网络的ViaSHAP在表格数据上表现与当前最优算法相当；同时，在表格数据和图像数据上，其解释精度显著优于流行的近似算法FastSHAP。
原文摘要 · Abstract (English)
Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To overcome this, a novel method, called ViaSHAP, is proposed, that learns a function to compute Shapley values, from which the predictions can be derived directly by summation. Two approaches to implement the proposed method are explored; one based on the universal approximation theorem and the other on the Kolmogorov-Arnold representation theorem. Results from a large-scale empirical investigation are presented, showing that ViaSHAP using Kolmogorov-Arnold Networks performs on par with state-of-the-art algorithms for tabular data. It is also shown that the explanations of ViaSHAP are significantly more accurate than the popular approximator FastSHAP on both tabular data and images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。