arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.02886cs.LGcs.AI
收藏

概念瓶颈专家混合模型

Mixture of Concept Bottleneck Experts

University of Padua(帕多瓦大学)
Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Johannes Schneider, Danilo Giordano, … 展开作者

Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Johannes Schneider, Danilo Giordano, Mateo Espinosa Zarlenga, Pietro Barbiero

AI总结:

提出概念瓶颈专家混合模型(M-CBE),通过引入多个专家表达式和灵活的函数形式,在保持可解释性的同时提升预测精度和适应性。

摘要:

概念瓶颈模型(CBM)通过将预测基于人类可理解的概念来促进可解释性。然而,现有的CBM通常将其任务预测器限制为单个表达式,其函数形式是预先设定的,这限制了预测精度和对不同用户需求的适应性。我们提出了概念瓶颈专家混合模型(M-CBE),这是一个沿两个维度推广现有CBM的框架:任务预测器用于将概念映射到任务的表达式数量(称为专家),以及每个表达式所采用的函数形式,从而揭示了该设计空间中一个未被充分探索的区域。我们通过实例化两个新颖的模型来研究这一区域:线性M-CBE,它学习一组有限的线性表达式;以及符号M-CBE,它利用符号回归从数据中发现专家函数,受限于用户指定的算子词汇表。实证评估表明,改变表达式的数量及其函数形式为导航精度-可解释性权衡提供了一个稳健的框架。

英文摘要:

Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically constrain their task predictor to a single expression whose functional form is set a priori, limiting both predictive accuracy and adaptability to diverse user needs. We propose Mixture of Concept Bottleneck Experts (M-CBE), a framework that generalizes existing CBMs along two dimensions: the number of expressions, referred to as experts, employed by the task predictor to map concepts to the task, and the functional form each expression takes, thus exposing an underexplored region of this design space. We investigate this region by instantiating two novel models: Linear M-CBE, which learns a finite set of linear expressions, and Symbolic M-CBE, which leverages symbolic regression to discover expert functions from data subject to user-specified operator vocabularies. Empirical evaluation demonstrates that varying the number of expressions and their functional form provides a robust framework for navigating the accuracy-interpretability trade-off.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑