用统计方法自动剔除训练中的异常数据，提升模型泛化能力
Z-Error Loss for Training Neural Networks
- 基于批次统计识别并屏蔽分布外样本
- 显著降低异常值对梯度的干扰
- 适合数据质量参差的场景，辅助数据清洗
异常值会通过传播错误梯度给神经网络训练带来严重挑战，从而损害模型性能与泛化能力。我们提出Z-Error Loss，一种基于统计原理的方法，通过在每个批次中识别分布外的数据点并屏蔽其贡献，来最小化异常值的影响。该方法利用批次级统计量自动检测并排除异常样本，使模型能够专注于学习真实数据结构。该方法具备鲁棒性，可自适应数据质量，并为数据整理与清洗提供有价值的诊断信息。
原文摘要 · Abstract (English)
Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that minimizes outlier influence during training by masking the contribution of data points identified as out-of-distribution within each batch. This method leverages batch-level statistics to automatically detect and exclude anomalous samples, allowing the model to focus its learning on the true underlying data structure. Our approach is robust, adaptive to data quality, and provides valuable diagnostics for data curation and cleaning.
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。