用能量模型和量化向量提升概念瓶颈模型的可靠性与准确性
EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
- 引入能量模型与量化激活向量实现概率化概念编码
- 在多个基准数据集上同时提升概念与任务准确率
- 适合关注可解释性、需人机协作的AI系统开发者
可信赖AI系统的需求推动了对可解释深度神经网络的研究。概念瓶颈模型（CBMs）通过利用人类可理解的概念来增强可解释性，受到广泛关注。然而，现有CBMs因概念编码的确定性及概念不一致性，导致预测不准确。本文提出EQ-CBM，一种新框架，通过基于能量模型（EBMs）的概率化概念编码与量化概念激活向量（qCAVs）提升CBMs性能。该方法有效捕捉不确定性，提高预测可靠性与准确性。通过qCAVs，模型在概念编码中选择同质向量，使任务表现更明确，支持更高程度的人类干预。在基准数据集上的实证结果表明，本方法在概念准确率与任务准确率上均优于现有最先进方法。
原文摘要 · Abstract (English)
The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance interpretability. However, existing CBMs face challenges due to deterministic concept encoding and reliance on inconsistent concepts, leading to inaccuracies. We propose EQ-CBM, a novel framework that enhances CBMs through probabilistic concept encoding using energy-based models (EBMs) with quantized concept activation vectors (qCAVs). EQ-CBM effectively captures uncertainties, thereby improving prediction reliability and accuracy. By employing qCAVs, our method selects homogeneous vectors during concept encoding, enabling more decisive task performance and facilitating higher levels of human intervention. Empirical results using benchmark datasets demonstrate that our approach outperforms the state-of-the-art in both concept and task accuracy.
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。