提出可解释逻辑网络的可视化方法，精准定位影响决策的输入
eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks
- 基于电路分析思想，生成激活特定功能的输入模式图
- 使模型规模减小87%，推理时间缩短8%，误判率仅降3.8%
- 适合医疗、国防等需高可信度决策的场景
将深度神经网络（DNN）约束为每个节点学习单一逻辑类型，如DiffLogic架构所示，可开启针对模型特性的解释技术，缓解DNN固有的复杂性。受计算机工程中电路分析原理启发，本文提出eXpLogic算法，生成揭示激活特定功能的输入模式的显著性图。eXpLogic解释具备三方面优势：(1) 明确展示导致决策的输入集合，有助于理解误报与漏报；(2) 突出激活特定输出的常见输入模式；(3) 用于压缩网络规模，提升类别特异性推理效率。为评估该显著性图，我们引入量化指标SwitchDist，衡量输入变化至模型分类结果切换的距离，并以此对比Vanilla Gradients（VG）和Integrated Gradient（IG）方法。实验表明，eXpLogic在预测哪些输入会改变分类得分方面表现更优。使用该方法可使网络规模减少87%，推理时间降低8%，对类别特异性预测影响仅-3.8%。本工作为机器学习领域提供启示：特定DNN架构能促进可解释性，对医疗、国防、法律等领域具有重要价值。
原文摘要 · Abstract (English)
Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs. Inspired by principles of circuit analysis from computer engineering, this work presents an algorithm (eXpLogic) for producing saliency maps which explain input patterns that activate certain functions. The eXpLogic explanations: (1) show the exact set of inputs responsible for a decision, which helps interpret false negative and false positive predictions, (2) highlight common input patterns that activate certain outputs, and (3) help reduce the network size to improve class-specific inference. To evaluate the eXpLogic saliency map, we introduce a metric that quantifies how much an input changes before switching a model's class prediction (the SwitchDist) and use this metric to compare eXpLogic against the Vanilla Gradients (VG) and Integrated Gradient (IG) methods. Generally, we show that eXpLogic saliency maps are better at predicting which inputs will change the class score. These maps help reduce the network size and inference times by 87\% and 8\%, respectively, while having a limited impact (-3.8\%) on class-specific predictions. The broader value of this work to machine learning is in demonstrating how certain DNN architectures promote explainability, which is relevant to healthcare, defense, and law.
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。