快速计算神经网络概念激活向量，提速超46倍。
FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
- 用新方法加速概念激活向量计算，理论保证等效于传统SVM方法
- 平均提速46.4倍，最高达63.6倍，结果稳定且性能相近
- 适合需要大规模解释深度模型的研究者和工程师
人类理解世界依赖于物体、模式、形状等概念。基于此，概念可解释性方法试图分析深度神经网络表征与人类可理解概念之间的关系。其中，概念激活向量（CAVs）是关键工具，用于判断模型是否学习了特定概念。然而，现有CAV计算方法在大规模高维架构中存在显著计算成本与时间开销。为此，我们提出FastCAV，通过理论支持的优化策略，使CAV提取速度平均提升46.4倍，最高达63.6倍。实验表明，FastCAV生成的CAVs在性能上与传统SVM方法相当，同时更高效稳定。在下游概念解释任务中，FastCAV可直接替代原有方法并获得相似洞察。我们进一步展示其可用于追踪模型训练过程中概念演化过程，开启此前难以实现的大规模模型可解释性研究。
原文摘要 · Abstract (English)
Concepts such as objects, patterns, and shapes are how humans understand the world. Building on this intuition, concept-based explainability methods aim to study representations learned by deep neural networks in relation to human-understandable concepts. Here, Concept Activation Vectors (CAVs) are an important tool and can identify whether a model learned a concept or not. However, the computational cost and time requirements of existing CAV computation pose a significant challenge, particularly in large-scale, high-dimensional architectures. To address this limitation, we introduce FastCAV, a novel approach that accelerates the extraction of CAVs by up to 63.6x (on average 46.4x). We provide a theoretical foundation for our approach and give concrete assumptions under which it is equivalent to established SVM-based methods. Our empirical results demonstrate that CAVs calculated with FastCAV maintain similar performance while being more efficient and stable. In downstream applications, i.e., concept-based explanation methods, we show that FastCAV can act as a replacement leading to equivalent insights. Hence, our approach enables previously infeasible investigations of deep models, which we demonstrate by tracking the evolution of concepts during model training.
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。