解决推荐系统中特征缩放不一致导致的排名偏差问题。
Scale-Invariant Learning-to-Rank
- 用深宽网络结构保证训练与预测时的尺度不变性
- 在缩放不一致情况下仍保持优于传统方法的排序效果
- 适合需要稳定线上推理的工业级推荐系统
在 Expedia 平台，学习排序（LTR）模型用于优化搜索结果、房源房间、设施和图片的排序展示。部署中的主要挑战是确保训练与生产数据间特征缩放的一致性，否则会导致排序不可靠。尽管标准化和批归一化能缓解此问题，但在生产环境中因延迟高且难以实现分布式实时推理而不可行。为此，我们提出一种尺度不变的 LTR 框架，结合深度与浅层神经网络，数学上保证模型在训练和预测阶段均具备尺度不变性。我们在模拟真实场景中通过扰动测试集注入特征尺度问题进行评估，结果显示，即使存在训练-测试尺度不一致，使用该框架仍优于无框架的情况。
原文摘要 · Abstract (English)
At Expedia, learning-to-rank (LTR) models plays a key role on our website in sorting and presenting information more relevant to users, such as search filters, property rooms, amenities, and images. A major challenge in deploying these models is ensuring consistent feature scaling between training and production data, as discrepancies can lead to unreliable rankings when deployed. Normalization techniques like feature standardization and batch normalization could address these issues but are impractical in production due to latency impacts and the difficulty of distributed real-time inference. To address consistent feature scaling issue, we introduce a scale-invariant LTR framework which combines a deep and a wide neural network to mathematically guarantee scale-invariance in the model at both training and prediction time. We evaluate our framework in simulated real-world scenarios with injected feature scale issues by perturbing the test set at prediction time, and show that even with inconsistent train-test scaling, using framework achieves better performance than without.
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。