让表格模型实时生成解释，速度比传统方法快千倍。
Real-Time Explanations for Tabular Foundation Models
- 将谢林值回归嵌入模型架构，一次前向传播同时输出预测和解释。
- 解释精度高（R²=0.96，余弦相似度0.99），耗时仅0.06秒。
- 适合需要快速交互式分析的科研与工业场景。
可解释性是科学机器学习的核心，理解模型为何做出预测有助于假设生成与验证。尽管表格基础模型表现优异，现有解释方法如SHAP计算成本高，限制了交互式探索。我们提出ShapPFN，一种将谢林值回归直接集成到模型架构中的基础模型，可在单次前向传播中同时生成预测与解释。在标准基准上，ShapPFN实现竞争性性能，解释保真度高（R²=0.96，余弦相似度=0.99），速度比KernelSHAP快1000倍以上（0.06秒 vs 610秒）。代码已公开于https://github.com/kunumi/ShapPFN。
原文摘要 · Abstract (English)
Interpretability is central for scientific machine learning, as understanding \emph{why} models make predictions enables hypothesis generation and validation. While tabular foundation models show strong performance, existing explanation methods like SHAP are computationally expensive, limiting interactive exploration. We introduce ShapPFN, a foundation model that integrates Shapley value regression directly into its architecture, producing both predictions and explanations in a single forward pass. On standard benchmarks, ShapPFN achieves competitive performance while producing high-fidelity explanations ($R^2$=0.96, cosine=0.99) over 1000\times faster than KernelSHAP (0.06s vs 610s). Our code is available at https://github.com/kunumi/ShapPFN
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。