提出高阶特征归因理论，揭示模型交互作用的可解释性新路径。
Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
- 基于积分梯度构建高阶特征归因框架，捕捉特征间复杂交互
- 理论证明该方法与统计学及拓扑信号处理存在深层关联
- 适用于需分析特征协同效应的复杂模型解释场景
特征归因是机器学习模型训练后的一种分析方法，用于评估输入特征对输出预测的贡献。当特征独立时，其解释清晰；但当模型涉及交互（如乘积关系或联合贡献）时，解释变得模糊。本文提出一种基于积分梯度（Integrated Gradients, IG）的高阶特征归因通用理论，建立在可解释人工智能现有框架之上。该理论揭示了与统计学和拓扑信号处理之间的自然联系，并提供多个理论结果以支撑其有效性，同时在若干示例中进行了验证。
原文摘要 · Abstract (English)
Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it becomes less clear when the predictive model involves interactions, such as multiplicative relationships or joint feature contributions. In this work, we propose a general theory of higher-order feature attribution, which we develop on the foundation of Integrated Gradients (IG). This work extends existing frameworks in the literature on explainable AI. When using IG as the method of feature attribution, we discover natural connections to statistics and topological signal processing. We provide several theoretical results that establish the theory, and we validate our theory on a few examples.
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。