用可解释AI识别并消除数据不平衡下的虚假关联
Imbalanced Classification through the Lens of Spurious Correlations
- 通过反事实解释定位不平衡时出现的虚假相关性
- 在三个数据集上达到与主流方法相当的分类效果
- 揭示了少数类因信息不足导致的欺骗性模型行为
数据不平衡是机器学习中的基本挑战，常导致分类性能不可靠。现有方法多聚焦于重采样或损失加权，而本文将不平衡视为放大‘聪明汉效应’（Clever Hans, CH）的数据条件，源于少数类定义不充分。我们提出一种基于反事实解释的方法，利用可解释AI联合识别并消除不平衡下产生的CH效应。实验在三个数据集上验证了该方法的竞争力，并揭示了不平衡如何诱发虚假相关性，这一视角在现有研究中长期被忽视。
原文摘要 · Abstract (English)
Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighting schemes, we view imbalance as a data condition that amplifies Clever Hans (CH) effects by underspecification of minority classes. In a counterfactual explanations-based approach, we propose to leverage Explainable AI to jointly identify and eliminate CH effects emerging under imbalance. Our method achieves competitive classification performance on three datasets and demonstrates how CH effects emerge under imbalance, a perspective largely overlooked by existing approaches.
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。