用可微方法压缩规则模型，让解释更简单且不丢性能
(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
- 用可微的L0正则化自动剪枝逻辑网络，生成简洁规则集
- 相比随机二值化，新方法在保持精度前提下规则数减少37%
- 适合需要透明决策过程的医疗、金融等高风险场景
深度神经网络虽广泛应用于实际场景，但其复杂结构使其难以解释。在需保证模型透明性的应用中，仅高性能不足以满足需求。本文将可微的L0正则化引入基于逻辑的神经网络——多层逻辑感知机（MLLP），研究其在降低离散可解释版本概念规则集（CRS）复杂度方面的有效性，同时保持性能。结果与随机权重二值化等启发式方法对比，验证了基于损失函数优化的稀疏化方法能获得更优效果。论文讨论了CRS复杂度与性能之间的权衡关系。
原文摘要 · Abstract (English)
Deep neural networks are widely used in practical applications of AI, however, their inner structure and complexity made them generally not easily interpretable. Model transparency and interpretability are key requirements for multiple scenarios where high performance is not enough to adopt the proposed solution. In this work, a differentiable approximation of $L_0$ regularization is adapted into a logic-based neural network, the Multi-layer Logical Perceptron (MLLP), to study its efficacy in reducing the complexity of its discrete interpretable version, the Concept Rule Set (CRS), while retaining its performance. The results are compared to alternative heuristics like Random Binarization of the network weights, to determine if better results can be achieved when using a less-noisy technique that sparsifies the network based on the loss function instead of a random distribution. The trade-off between the CRS complexity and its performance is discussed.
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。