按群体调阈值比数据增广更有效，提升不平衡学习的公平性与准确率。
Beyond Synthetic Augmentation: Group-Aware Threshold Calibration for Robust Balanced Accuracy in Imbalanced Learning
- 为不同群体设置专属决策阈值，动态优化整体与最差群体表现的平衡。
- 在7种模型上实现1.5%-4%更高平衡准确率，最差群体表现显著改善。
- 方法简单可解释，适合关注模型公平性的实际应用者。
类别不平衡仍是机器学习中的核心挑战，传统解决方案常带来新问题。我们发现，基于群体的阈值校准——即为不同人口群体设定不同决策阈值——相比合成数据生成方法展现出更强鲁棒性。通过大量实验表明，群体特定阈值在平衡准确率上比SMOTE和CT-GAN增强模型高出1.5%-4%，同时显著提升最差群体的平衡准确率。与全局单一阈值不同，该方法在平衡准确率与最差群体平衡准确率之间优化帕累托前沿，实现细粒度控制。关键发现是，将群体阈值应用于合成数据后收益极小，说明二者本质上冗余。研究涵盖线性、树模型、实例基础及集成方法共七类模型，验证了该方法在简单性、可解释性和有效性上的优势。
原文摘要 · Abstract (English)
Class imbalance remains a fundamental challenge in machine learning, with traditional solutions often creating as many problems as they solve. We demonstrate that group-aware threshold calibration--setting different decision thresholds for different demographic groups--provides superior robustness compared to synthetic data generation methods. Through extensive experiments, we show that group-specific thresholds achieve 1.5-4% higher balanced accuracy than SMOTE and CT-GAN augmented models while improving worst-group balanced accuracy. Unlike single-threshold approaches that apply one cutoff across all groups, our group-aware method optimizes the Pareto frontier between balanced accuracy and worst-group balanced accuracy, enabling fine-grained control over group-level performance. Critically, we find that applying group thresholds to synthetically augmented data yields minimal additional benefit, suggesting these approaches are fundamentally redundant. Our results span seven model families including linear, tree-based, instance-based, and boosting methods, confirming that group-aware threshold calibration offers a simpler, more interpretable, and more effective solution to class imbalance.
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。