Joint Optimization of Ranking and Calibration with Contextualized Hybrid Model

TL;DR

This paper introduces JRC, a joint optimization method for ranking and calibration in CTR prediction models, improving both aspects by constraining logits and interpreting them as joint distributions, with proven theoretical benefits and real-world deployment.

Contribution

The paper proposes JRC, a novel approach that jointly optimizes ranking and calibration by constraining logits, maintaining their interpretability, and approximately optimizing a hybrid discriminative-generative objective.

Findings

JRC improves both ranking and calibration in CTR models.

Experimental results show significant performance gains on public and industrial datasets.

JRC has been successfully deployed in Alibaba's advertising platform since May 2022.

Abstract

Despite the development of ranking optimization techniques, pointwise loss remains the dominating approach for click-through rate prediction. It can be attributed to the calibration ability of the pointwise loss since the prediction can be viewed as the click probability. In practice, a CTR prediction model is also commonly assessed with the ranking ability. To optimize the ranking ability, ranking loss (e.g., pairwise or listwise loss) can be adopted as they usually achieve better rankings than pointwise loss. Previous studies have experimented with a direct combination of the two losses to obtain the benefit from both losses and observed an improved performance. However, previous studies break the meaning of output logit as the click-through rate, which may lead to sub-optimal solutions. To address this issue, we propose an approach that can Jointly optimize the Ranking and Calibration abilities (JRC for short). JRC improves the ranking ability by contrasting the logit value for the sample with different labels and constrains the predicted probability to be a function of the logit subtraction. We further show that JRC consolidates the interpretation of logits, where the logits model the joint distribution. With such an interpretation, we prove that JRC approximately optimizes the contextualized hybrid discriminative-generative objective. Experiments on public and industrial datasets and online A/B testing show that our approach improves both ranking and calibration abilities. Since May 2022, JRC has been deployed on the display advertising platform of Alibaba and has obtained significant performance improvements.