用图结构建模概念间关系，提升模型可解释性与干预效果
Graph Concept Bottleneck Models
- 构建隐含概念图，显式捕捉概念间的关联关系
- 在图像分类任务中准确率更高，且提供更丰富的结构化解释
- 适用于多种训练设置，适合需要可控干预的场景
概念瓶颈模型（CBMs）通过概念提供深度神经网络的显式解释，并支持通过概念干预调整预测结果。现有CBMs假设概念在给定标签下条件独立且彼此隔离，忽略了概念间潜在的内在关联。然而，实际应用中概念常具有相关性：改变一个概念会自然影响其关联概念。为此，我们提出图概念瓶颈模型（GraphCBMs），通过构建潜在概念图来显式建模概念间关系，可与传统CBM结合，在保持可解释性的前提下提升性能。实验证明，图概念瓶颈模型在真实世界图像分类任务中具有以下优势：(1) 分类性能更优，同时提供更丰富的概念结构信息以增强可解释性；(2) 可利用隐含概念图实现更有效的概念干预；(3) 在不同训练策略与网络架构下表现稳定。
原文摘要 · Abstract (English)
Concept Bottleneck Models (CBMs) provide explicit interpretations for deep neural networks through concepts and allow intervention with concepts to adjust final predictions. Existing CBMs assume concepts are conditionally independent given labels and isolated from each other, ignoring the hidden relationships among concepts. However, the set of concepts in CBMs often has an intrinsic structure where concepts are generally correlated: changing one concept will inherently impact its related concepts. To mitigate this limitation, we propose GraphCBMs: a new variant of CBM that facilitates concept relationships by constructing latent concept graphs, which can be combined with CBMs to enhance model performance while retaining their interpretability. Our experiment results on real-world image classification tasks demonstrate Graph CBMs offer the following benefits: (1) superior in image classification tasks while providing more concept structure information for interpretability; (2) able to utilize latent concept graphs for more effective interventions; and (3) robust in performance across different training and architecture settings.
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。