RIA: A Ranking-Infused Approach for Optimized listwise CTR Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917106541395968 |
|---|---|
| author | Zhang, Guoxiao Qu, Tan Li, Ao Ni, DongLin Xie, Qianlong Wang, Xingxing |
| author_facet | Zhang, Guoxiao Qu, Tan Li, Ao Ni, DongLin Xie, Qianlong Wang, Xingxing |
| contents | Reranking improves recommendation quality by modeling item interactions. However, existing methods often decouple ranking and reranking, leading to weak listwise evaluation models that suffer from combinatorial sparsity and limited representational power under strict latency constraints. In this paper, we propose RIA (Ranking-Infused Architecture), a unified, end-to-end framework that seamlessly integrates pointwise and listwise evaluation. RIA introduces four key components: (1) the User and Candidate DualTransformer (UCDT) for fine-grained user-item-context modeling; (2) the Context-aware User History and Target (CUHT) module for position-sensitive preference learning; (3) the Listwise Multi-HSTU (LMH) module to capture hierarchical item dependencies; and (4) the Embedding Cache (EC) module to bridge efficiency and effectiveness during inference. By sharing representations across ranking and reranking, RIA enables rich contextual knowledge transfer while maintaining low latency. Extensive experiments show that RIA outperforms state-of-the-art models on both public and industrial datasets, achieving significant gains in AUC and LogLoss. Deployed in Meituan advertising system, RIA yields a +1.69% improvement in Click-Through Rate (CTR) and a +4.54% increase in Cost Per Mille (CPM) in online A/B tests. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RIA: A Ranking-Infused Approach for Optimized listwise CTR Prediction Zhang, Guoxiao Qu, Tan Li, Ao Ni, DongLin Xie, Qianlong Wang, Xingxing Information Retrieval Artificial Intelligence Reranking improves recommendation quality by modeling item interactions. However, existing methods often decouple ranking and reranking, leading to weak listwise evaluation models that suffer from combinatorial sparsity and limited representational power under strict latency constraints. In this paper, we propose RIA (Ranking-Infused Architecture), a unified, end-to-end framework that seamlessly integrates pointwise and listwise evaluation. RIA introduces four key components: (1) the User and Candidate DualTransformer (UCDT) for fine-grained user-item-context modeling; (2) the Context-aware User History and Target (CUHT) module for position-sensitive preference learning; (3) the Listwise Multi-HSTU (LMH) module to capture hierarchical item dependencies; and (4) the Embedding Cache (EC) module to bridge efficiency and effectiveness during inference. By sharing representations across ranking and reranking, RIA enables rich contextual knowledge transfer while maintaining low latency. Extensive experiments show that RIA outperforms state-of-the-art models on both public and industrial datasets, achieving significant gains in AUC and LogLoss. Deployed in Meituan advertising system, RIA yields a +1.69% improvement in Click-Through Rate (CTR) and a +4.54% increase in Cost Per Mille (CPM) in online A/B tests. |
| title | RIA: A Ranking-Infused Approach for Optimized listwise CTR Prediction |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2511.21394 |