Entire-Space Variational Information Exploitation for Post-Click Conversion Rate Prediction

TL;DR

This paper introduces EVI, a novel framework for CVR prediction in recommender systems that effectively leverages unclicked samples through unbiased pseudo labels and variational information exploitation, improving accuracy.

Contribution

The paper proposes an entire-space variational information exploitation framework (EVI) that addresses sample bias and data sparsity in CVR estimation by using a conditional teacher and logit distillation.

Findings

EVI achieves a 2.25% average improvement over state-of-the-art methods.

EVI effectively utilizes unclicked samples for better CVR prediction.

Extensive experiments on six large datasets validate EVI's effectiveness.

Abstract

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.