发表机构
Huawei Türkiye R&D Center（华为土耳其研发中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对点击率预测模型早期训练崩溃问题，通过大规模工业数据集分析，发现降低学习率效果不佳，而控制特征稀疏性如去除高度稀疏特征、聚合罕见特征值可稳定训练，提升离线和在线性能。
AI 中文摘要
用于点击率预测的深度神经模型通常在第一个训练周期后验证性能急剧下降，尽管训练损失持续改善。这种不稳定性限制了有效学习和模型性能。本研究使用大规模工业数据集分析此行为并评估实际缓解策略。降低学习率效果有限，控制特征稀疏性有显著改善。去除高度稀疏特征和聚合罕见特征值可稳定训练，延长有效学习，提升离线评估指标和在线系统性能。
英文摘要
Deep neural models for click-through rate prediction often exhibit a sharp decline in validation performance immediately after the first training epoch despite continued improvement in training loss. This instability restricts effective learning and limits model performance. In this study, we analyze this behavior using large-scale industrial datasets and evaluate practical mitigation strategies. While reducing the learning rate provides only incremental gains, controlling feature sparsity yields substantial improvements. Removing highly sparse features and aggregating infrequent feature values stabilizes training, extends useful learning beyond a single epoch, and improves both offline evaluation metrics and online system performance.
Comments4 pages, 1 figure
