Enhancing Pre-Ranking Performance: Tackling Intermediary Challenges in Multi-Stage Cascading Recommendation Systems

Abstract

Large-scale search engines and recommendation systems utilize a three-stage cascading architecture-recall, pre-ranking, and ranking-to deliver relevant results within stringent latency limits. The pre-ranking stage is crucial for filtering a large number of recalled items into a manageable set for the ranking stage, greatly affecting the system's performance. Pre-ranking faces two intermediary challenges: Sample Selection Bias (SSB) arises when training is based on ranking stage feedback but the evaluation is on a broader recall dataset. Also, compared to the ranking stage, simpler pre-rank models may perform worse and less consistently. Traditional methods to tackle SSB issues include using all recall results and treating unexposed portions as negatives for training, which can be costly and noisy. To boost performance and consistency, some pre-ranking feature interaction enhancers don't fully fix consistency issues, while methods like knowledge distillation in ranking models ignore exposure bias. Our proposed framework targets these issues with three integral modules: Sample Selection, Domain Adaptation, and Unbiased Distillation. Sample Selection filters recall results to mitigate SSB and compute costs. Domain Adaptation enhances model robustness by assigning pseudo-labels to unexposed samples. Unbiased Distillation uses exposure-independent scores from Domain Adaptation to implement unbiased distillation for the pre-ranking model. The framework focuses on optimizing pre-ranking while maintaining training efficiency. We introduce new metrics for pre-ranking evaluation, while experiments confirm the effectiveness of our framework. Our framework is also deployed in real industrial systems.