Not All Candidates are Created Equal: A Heterogeneity-Aware Approach to Pre-ranking in Recommender Systems
Most large-scale recommender systems follow a multi-stage cascade of retrieval, pre-ranking, ranking, and re-ranking. A key challenge at the pre-ranking stage arises from the heterogeneity of training instances sampled from coarse-grained retrieval results, fine-grained ranking signals, and exposure feedback. Our analysis reveals that prevailing pre-ranking methods, which indiscriminately mix heterogeneous samples, suffer from gradient conflicts: hard samples dominate training while easy ones remain underutilized, leading to suboptimal performance. We further show that the common practice of uniformly scaling model complexity across all samples is inefficient, as it overspends computation on easy cases and slows training without proportional gains. To address these limitations, this paper presents Heterogeneity-Aware Adaptive Pre-ranking (HAP), a unified framework that mitigates gradient conflicts through conflict-sensitive sampling coupled with tailored loss design, while adaptively allocating computational budgets across candidates. Specifically, HAP disentangles easy and hard samples, directing each subset along dedicated optimization paths. Building on this separation, it first applies lightweight models to all candidates for efficient coverage, and further engages stronger models on the hard ones, maintaining accuracy while reducing cost. This approach not only improves pre-ranking effectiveness but also provides a practical perspective on scaling strategies in industrial recommender systems. HAP has been deployed in the Toutiao production system for 9 months, yielding up to 0.4% improvement in user app usage duration and 0.05% in active days, without additional computational cost. We also release a large-scale industrial hybrid-sample dataset to enable the systematic study of source-driven candidate heterogeneity in pre-ranking.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Ladder Loss for Coherent Visual-Semantic Embedding
For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all "irrelevant" candidates are uniformly pushed away from t…
RetrievalTripletLearning to Rank with Top-$K$ Fairness
Fairness in ranking models is crucial, as disparities in exposure can disproportionately affect protected groups. Most fairness-aware ranking systems focus on ensuring comparable average exposure for groups across the en…
Stochastic OptimizationRAGUEL: Recourse-Aware Group Unfairness Elimination
While machine learning and ranking-based systems are in widespread use for sensitive decision-making processes (e.g., determining job candidates, assigning credit scores), they are rife with concerns over unintended bias…
AttributecounterfactualDecision MakingFairness+1CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery
Large language models (LLMs) have created new opportunities to enhance the efficiency of scholarly activities; however, challenges persist in the ethical deployment of AI assistance, including (1) the trustworthiness of …
Practical Relative Order Attack in Deep Ranking
Recent studies unveil the vulnerabilities of deep ranking models, where an imperceptible perturbation can trigger dramatic changes in the ranking result. While previous attempts focus on manipulating absolute ranks of ce…
Adversarial AttackTriplet