重要性加权在真实数据分布偏移下效果有限，需谨慎使用。
Understand the Effect of Importance Weighting in Deep Learning on Dataset Shift
- 在合成数据上，加权影响早期决策边界，但训练时间长后作用减弱。
- CIFAR-10中仅L2正则化能保留加权效果，丢弃法无效。
- 复杂数据上加权无显著提升，揭示其实际应用的局限性。
我们评估了重要性加权在标签偏移和协变量偏移下的有效性。在二维合成数据（线性可分与月牙形）上使用逻辑回归和MLP，发现加权在训练初期显著影响决策边界，但随优化过程延长而逐渐失效。在具有各类别不平衡的CIFAR-10上，仅有L2正则化能保持加权效果，而丢弃法无效。在协变量偏移实验中，重要性加权未带来显著性能提升，凸显其在复杂数据上的挑战。研究结果质疑了重要性加权在真实世界分布偏移中的实用性。
原文摘要 · Abstract (English)
We evaluate the effectiveness of importance weighting in deep neural networks under label shift and covariate shift. On synthetic 2D data (linearly separable and moon-shaped) using logistic regression and MLPs, we observe that weighting strongly affects decision boundaries early in training but fades with prolonged optimization. On CIFAR-10 with various class imbalances, only L2 regularization (not dropout) helps preserve weighting effects. In a covariate-shift experiment, importance weighting yields no significant performance gain, highlighting challenges on complex data. Our results call into question the practical utility of importance weighting for real-world distribution shifts.
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。