通过变分信息蒸馏，提升点击后转化率预测的准确性
Entire-Space Variational Information Exploitation for Post-Click Conversion Rate Prediction
- 用条件全空间教师模型生成无偏伪标签
- 在六大数据集上平均提升2.25%性能
- 适合需要精准转化率建模的推荐系统研究者
在推荐系统中，点击后转化率（CVR）估计是建模用户偏好和评估推荐价值的关键任务。样本选择偏差（SSB）和数据稀疏性（DS）是该任务长期存在的挑战。当前的全空间方法通过知识蒸馏利用未点击样本，有望同时缓解上述问题。现有方法使用非转化、转化或自适应转化预测器为未点击样本生成伪标签，但忽略了这些伪标签的无偏性和信息局限性。为此，本文提出整个空间变分信息利用框架（EVI）用于CVR预测。首先，EVI采用条件全空间CVR教师模型生成无偏伪标签；随后，通过变分信息利用与logit蒸馏，将未点击空间的信息迁移到目标CVR估计器中。我们在六个大规模数据集上进行了广泛的离线实验，结果显示EVI相比最先进基线平均提升2.25%。
原文摘要 · Abstract (English)
In recommender systems, post-click conversion rate (CVR) estimation is an essential task to model user preferences for items and estimate the value of recommendations. Sample selection bias (SSB) and data sparsity (DS) are two persistent challenges for post-click conversion rate (CVR) estimation. Currently, entire-space approaches that exploit unclicked samples through knowledge distillation are promising to mitigate SSB and DS simultaneously. Existing methods use non-conversion, conversion, or adaptive conversion predictors to generate pseudo labels for unclicked samples. However, they fail to consider the unbiasedness and information limitations of these pseudo labels. Motivated by such analysis, we propose an entire-space variational information exploitation framework (EVI) for CVR prediction. First, EVI uses a conditional entire-space CVR teacher to generate unbiased pseudo labels. Then, it applies variational information exploitation and logit distillation to transfer non-click space information to the target CVR estimator. We conduct extensive offline experiments on six large-scale datasets. EVI demonstrated a 2.25\% average improvement compared to the state-of-the-art baselines.
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。