论文提出原型方法作为表格数据可解释性的补充路径
Overlooked and Underutilized: Prototypes are the Missing Piece in Tabular XAI
做表格数据模型审计的朋友可以看看这篇。它说清了为什么特征归因对非专家太费劲,以及怎么用原型加语义分组降低理解门槛,还给了 Geometric Validity Triad 这个新视角。适合 XAI 研究者和风控、医疗等高门槛场景的建模团队。
一篇新论文指出,表格数据的可解释 AI(XAI)长期依赖特征归因方法,非专家用户需要逐条理解数十个孤立特征,认知负担过高。
作者主张将原型(prototypes)纳入解释流程,通过把相关特征分组为有界的子空间,形成人类可理解的语义单元,替代孤立特征。论文从两个角度论证:认知上,prototypical parts 符合 Rosch 的范畴化理论与 Kahneman 的 System 1 思维,能降低认知负荷;
技术上,作者提出 Geometric Validity Triad,说明原型能验证数据流形——这是现有方法常忽略的维度。论文最后列出基于原型的方法的开放挑战与潜在解决方案,并倡导将相似性推理与特征级审计结合的复合解释管线。
Overlooked and Underutilized: Prototypes are the Missing Piece in Tabular XAI
Explainable AI (XAI) is frequently applied to high-stakes tabular data, yet the field relies heavily on feature attribution methods. While these approaches offer technical transparency, evaluating dozens of isolated features demands excessive cognitive effort from non-expert users. In this paper, we argue that prototypes remain overlooked and underutilized, and should be integrated as a complementary, intuitive gateway to auditing complex machine learning models. Although entire exemplars function as an intuitive baseline for prototype-based explanations, we highlight prototypical parts as particularly valuable for tabular data. By grouping related features into bounded subspaces, prototypical parts technically embody human-understandable concepts, replacing isolated features with cohesive semantic units. We support this integration through two primary lenses. Cognitively, these parts align with Rosch's categorization theory and Kahneman's System 1 thinking to naturally reduce cognitive load for humans. Then, we introduce a Geometric Validity Triad to conceptualize why prototypes validate the data manifold - a critical dimension often neglected by existing methods. We contend that making tabular XAI genuinely comprehensible requires shifting toward composite explanation pipelines that pair intuitive similarity-based reasoning with rigorous feature-level auditing. The paper concludes by outlining open challenges of prototype-based methods and discussing potential solutions to guide future research.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include XAI, interpretability, tabular data, feature attribution.
Source attribution: curated from arXiv cs.LG (@Jacek Karolczak, Jerzy Stefanowski).