零样本实现可解释的模型预测，无需训练即可理解输入与标签间语义关系。
Zero-shot Concept Bottleneck Models
- 利用海量网络词汇构建概念库，动态检索输入相关概念。
- 通过稀疏线性回归筛选关键概念，实现零样本标签推断。
- 适合需要快速可解释推理且无标注数据的场景。
概念瓶颈模型（CBMs）具备内在可解释性和可干预性，通过高层语义概念的中间预测来解释最终标签结果。然而，传统方法需在目标任务上训练以学习输入到概念、概念到标签的映射，依赖目标数据集收集和训练资源。本文提出零样本概念瓶颈模型（Z-CBMs），可在完全零样本条件下预测概念与标签，无需训练神经网络。Z-CBMs采用由数百万网络词汇组成的大型概念库，描述跨领域的任意输入。对于输入到概念的映射，引入概念检索机制，通过跨模态搜索在概念库中动态定位相关概念。在概念到标签的推理阶段，采用概念回归，通过稀疏线性回归从检索出的概念中筛选关键概念。大量实验表明，所提Z-CBMs可在无需额外训练的情况下提供可解释且可干预的概念。代码将公开于 https://github.com/yshinya6/zcbm。
原文摘要 · Abstract (English)
Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models, which explain their final label prediction by the intermediate prediction of high-level semantic concepts. However, they require target task training to learn input-to-concept and concept-to-label mappings, incurring target dataset collections and training resources. In this paper, we present zero-shot concept bottleneck models (Z-CBMs), which predict concepts and labels in a fully zero-shot manner without training neural networks. Z-CBMs utilize a large-scale concept bank, which is composed of millions of vocabulary extracted from the web, to describe arbitrary input in various domains. For the input-to-concept mapping, we introduce concept retrieval, which dynamically finds input-related concepts by the cross-modal search on the concept bank. In the concept-to-label inference, we apply concept regression to select essential concepts from the retrieved concepts by sparse linear regression. Through extensive experiments, we confirm that our Z-CBMs provide interpretable and intervenable concepts without any additional training. Code will be available at https://github.com/yshinya6/zcbm.
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。