用离散优化让模型用少数特征解释图像分类，全局可懂且更准。
QPM: Discrete Optimization for Globally Interpretable Image Classification
- 用离散优化找出每类仅5个左右的二值特征，跨类共享提升可比性。
- 在小到大尺度数据集上实现前所未有的全局可解释性，同时保持高准确率。
- 适合需要透明决策的场景，如医疗、自动驾驶等安全关键应用。
理解深度神经网络的分类决策（尤其在安全关键场景中）日益重要。现有模型只能局部解释单一预测，而提供准确模型的全局忠实解释仍是开放难题。为此，我们提出二次规划增强模型（QPM），学习全局可解释的类别表示。QPM将每个类别用极少数（通常为5个）二值特征表示，这些特征也分配给其他类别，确保类别间具有可比性的对比表示。该紧凑的二值分配通过基于预定义相似性度量和可解释性约束的离散优化求得。所得最优分配用于微调多样化特征，使每个特征成为所分配类别的共享通用概念。大量实验证明，QPM在小规模与大规模数据集上均实现前所未有的全局可解释性，并在可解释模型的准确性上达到新高度。
原文摘要 · Abstract (English)
Understanding the classifications of deep neural networks, e.g. used in safety-critical situations, is becoming increasingly important. While recent models can locally explain a single decision, to provide a faithful global explanation about an accurate model's general behavior is a more challenging open task. Towards that goal, we introduce the Quadratic Programming Enhanced Model (QPM), which learns globally interpretable class representations. QPM represents every class with a binary assignment of very few, typically 5, features, that are also assigned to other classes, ensuring easily comparable contrastive class representations. This compact binary assignment is found using discrete optimization based on predefined similarity measures and interpretability constraints. The resulting optimal assignment is used to fine-tune the diverse features, so that each of them becomes the shared general concept between the assigned classes. Extensive evaluations show that QPM delivers unprecedented global interpretability across small and large-scale datasets while setting the state of the art for the accuracy of interpretable models.
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。