让模型从原始数据直接学规则，无需标注特征名
Differentiable Rule Induction from Raw Sequence Inputs
- 用自监督聚类+可微逻辑编程，从原始序列自动提取符号变量
- 在时间序列和图像上学到可解释的泛化规则，准确率显著提升
- 适合需要透明决策过程的场景，如医疗、金融风控
基于规则的学习模型因结构透明而广泛应用于可解释性要求高的场景。归纳逻辑编程（ILP）通过事实推导规则，保持可解释性。可微分ILP模型利用神经网络提升鲁棒性和可扩展性，但多数方法依赖符号数据集，在直接从原始数据学习时面临显式标签泄露问题：无法在无输入特征标签监督的情况下将连续输入映射到符号变量。本文通过将自监督可微聚类模型与新型可微分ILP模型结合，实现无需显式标签泄露即可从原始数据中进行规则学习。所学规则能有效通过特征描述原始数据。实验表明，该方法能直观且精确地从时间序列和图像数据中学习出泛化规则。
原文摘要 · Abstract (English)
Rule learning-based models are widely used in highly interpretable scenarios due to their transparent structures. Inductive logic programming (ILP), a form of machine learning, induces rules from facts while maintaining interpretability. Differentiable ILP models enhance this process by leveraging neural networks to improve robustness and scalability. However, most differentiable ILP methods rely on symbolic datasets, facing challenges when learning directly from raw data. Specifically, they struggle with explicit label leakage: The inability to map continuous inputs to symbolic variables without explicit supervision of input feature labels. In this work, we address this issue by integrating a self-supervised differentiable clustering model with a novel differentiable ILP model, enabling rule learning from raw data without explicit label leakage. The learned rules effectively describe raw data through its features. We demonstrate that our method intuitively and precisely learns generalized rules from time series and image data.
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。