用表格大模型加速条件谢尔普利值计算，效率显著提升。
Computing Conditional Shapley Values Using Tabular Foundation Models
- 利用上下文学习的表格基础模型，免于重训练即可估算条件期望。
- 在多数数据集上性能优于现有方法，运行时间仅为几分之一。
- 适合需要快速解释且特征相关的机器学习场景。
谢尔普利值已成为可解释人工智能的核心工具，但其计算成本高昂，尤其在特征存在依赖关系时。评估需近似大量条件期望，传统方法依赖蒙特卡洛积分或回归，而后者因每次条件期望需重新训练，难以利用深度学习。表格基础模型（如TabPFN）通过上下文学习克服此瓶颈，无需重训练即可快速估算条件期望。本文使用多种TabPFN变体计算谢尔普利值，并在模拟与真实数据集上与当前最优方法对比。多数情况下，TabPFN表现最佳；即使未胜出，也仅略逊一筹，但耗时仅为几分之一。文章还探讨了进一步改进方向，以及如何更适配条件谢尔普利值估计任务。
原文摘要 · Abstract (English)
Shapley values have become a cornerstone of explainable AI, but they are computationally expensive to use, especially when features are dependent. Evaluating them requires approximating a large number of conditional expectations, either via Monte Carlo integration or regression. Until recently it has not been possible to fully exploit deep learning for the regression approach, because retraining for each conditional expectation takes too long. Tabular foundation models such as TabPFN overcome this computational hurdle by leveraging in-context learning, so each conditional expectation can be approximated without any re-training. In this paper, we compute Shapley values with multiple variants of TabPFN and compare their performance with state-of-the-art methods on both simulated and real datasets. In most cases, TabPFN yields the best performance; where it does not, it is only marginally worse than the best method, at a fraction of the runtime. We discuss further improvements and how tabular foundation models can be better adapted specifically for conditional Shapley value estimation.
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。