提出新方法自动提取与模型决策一致的概念，提升解释可信度。
FACE: Faithful Automatic Concept Extraction
- 用KL散度约束非负矩阵分解，确保概念与模型预测对齐
- 在图像分类任务中，概念解释的忠实度和稀疏性均优于现有方法
- 适合需要可解释性强的AI应用，如医疗诊断、自动驾驶
通过基于概念的解释，深度神经网络可实现从低层特征到高层人类可理解语义的桥梁。然而，现有自动概念发现方法常无法与模型真实决策过程对齐，导致解释不忠实。本文提出FACE（Faithful Automatic Concept Extraction），在非负矩阵分解（NMF）中引入Kullback-Leibler（KL）散度正则项，确保模型原始输出与概念基输出之间的一致性。不同于仅依赖编码器激活的方法，FACE在概念学习中融入分类器监督，强制预测一致性，从而实现可信解释。理论分析表明，最小化KL散度可限制预测分布偏差，促进概念空间中的忠实局部线性。在ImageNet、COCO和CelebA数据集上的系统评估显示，FACE在忠实度与稀疏性指标上全面超越现有方法。
原文摘要 · Abstract (English)
Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing automatic concept discovery methods often fail to align these extracted concepts with the model's true decision-making process, thereby compromising explanation faithfulness. In this work, we propose FACE (Faithful Automatic Concept Extraction), a novel framework that augments Non-negative Matrix Factorization (NMF) with a Kullback-Leibler (KL) divergence regularization term to ensure alignment between the model's original and concept-based predictions. Unlike prior methods that operate solely on encoder activations, FACE incorporates classifier supervision during concept learning, enforcing predictive consistency and enabling faithful explanations. We provide theoretical guarantees showing that minimizing the KL divergence bounds the deviation in predictive distributions, thereby promoting faithful local linearity in the learned concept space. Systematic evaluations on ImageNet, COCO, and CelebA datasets demonstrate that FACE outperforms existing methods across faithfulness and sparsity metrics.
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。