让概念瓶颈模型学会在不确定时自动过滤错误信息，提升解释可信度。
ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models
- 用不确定性动态控制概念间关系的推理过程
- 在概念缺失或错误时仍能保持准确预测与解释
- 适合需要可靠可解释性的实际应用场景
概念瓶颈模型（CBMs）通过将预测基于人类可理解的概念，提供可解释性框架，支持语义分析和测试时干预。近期变体通过更丰富的概念表征、不确定性估计和依赖建模提升了性能，但面对不可靠概念状态的鲁棒推理仍不充分。若缺乏此类推理，错误的语义证据可能在瓶颈中传播，损害解释与下游预测。为此，我们提出ReCBM，一种面向CBMs的不确定性门控关系推理框架。ReCBM在瓶颈中引入语义定义的概念关系，利用不确定性指导其优化。通过建模共现、蕴含与排斥关系，明确概念间证据传递机制，同时由不确定性调节每个概念的贡献。跨多种数据集的实验表明，ReCBM在概念缺失或翻转情况下提升了概念与任务恢复能力，支持不确定性感知的干预，并提取出紧凑的任务相关概念子集，且未降低下游性能。
原文摘要 · Abstract (English)
Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention. Recent variants have improved CBMs through richer concept representations, uncertainty estimation, and dependency modeling. However, robust reasoning under unreliable concept states remains underexplored. Without such reasoning, misleading semantic evidence can propagate through the bottleneck, compromising both explanations and downstream predictions. To address this issue, we propose ReCBM, an uncertainty-gated relational reasoning framework for CBMs. ReCBM introduces semantically defined concept relations into the bottleneck and uses uncertainty to guide their refinement. By modeling co-occurrence, implication, and exclusion, ReCBM specifies how evidence is exchanged across concepts, while uncertainty modulates the contribution of each concept during this process. Experiments across diverse datasets showed that ReCBM improved concept and task recovery under missing and flipped concepts, supported uncertainty-aware intervention, and extracted compact task-relevant concept subsets without degrading downstream performance.
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。