提出可解释的数据增强方法，让少数类样本生成更合理且透明。
Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning
- 从训练模型提取决策规则，指导数据生成
- 在多个数据集上优于传统过采样方法
- 生成样本逻辑合理，结果可解释，适合医疗等高风险领域
许多机器学习分类任务面临数据不平衡问题，常采用过采样技术提升模型性能。但现有方法易生成不现实或不可行的样本，且过程黑箱化，难以追踪效果和调整。为此，本文提出决策谓词图数据增强（DPG-da）框架，通过从训练模型中提取可解释的决策谓词，捕获领域规则，并在样本生成中施加约束，确保过采样数据保持多样性、满足约束且可解释。在合成与真实世界基准数据集上的实验表明，DPG-da持续优于传统过采样方法，同时保证逻辑有效性，并提供清晰的生成过程解释。
原文摘要 · Abstract (English)
Many machine learning classification tasks involve imbalanced datasets, which are often subject to over-sampling techniques aimed at improving model performance. However, these techniques are prone to generating unrealistic or infeasible samples. Furthermore, they often function as black boxes, lacking interpretability in their procedures. This opacity makes it difficult to track their effectiveness and provide necessary adjustments, and they may ultimately fail to yield significant performance improvements. To bridge this gap, we introduce the Decision Predicate Graphs for Data Augmentation (DPG-da), a framework that extracts interpretable decision predicates from trained models to capture domain rules and enforce them during sample generation. This design ensures that over-sampled data remain diverse, constraint-satisfying, and interpretable. In experiments on synthetic and real-world benchmark datasets, DPG-da consistently improves classification performance over traditional over-sampling methods, while guaranteeing logical validity and offering clear, interpretable explanations of the over-sampled 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。