Research map / Label-efficient and robust learning / Recognition and long-tail
Dual-Horizon Interest Model for Unified Search and Recommendation
Wenhao Zhu, Yuxin Li, Shuo Wang, Hao Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add long-term interest in recommendation branch (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3593 -> 0.3820 | Improved |
| add short-term interest in recommendation branch (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3666 -> 0.3820 | Improved |
| add long-term interest in search branch (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3616 -> 0.3820 | Improved |
| add short-term interest in search branch (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3572 -> 0.3820 | Improved |
| add cross-scene dual-horizon interest fusion (CSF) (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3536 -> 0.3820 | Improved |
| add recommendation intra-scenario contrastive loss (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3744 -> 0.3820 | Improved |
| add search intra-scenario contrastive loss (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3448 -> 0.3820 | Improved |
| add inter-scenario contrastive loss (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3627 -> 0.3820 | Improved |
| add LQ loss (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3676 -> 0.3820 | Improved |
| add PLE multi-task framework instead of independent MLPs (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3531 -> 0.3820 | Improved |
| add joint search and recommendation modeling instead of single-scenario (ablation) | DHIM · KuaiSAR | NDCG@5 (overall): 0.3197 -> 0.3820 | Improved |
| add short-term interest in recommendation branch (ablation) | DHIM · KuaiSAR search | NDCG@5: 0.6129 -> 0.6118 | No clear effect |
Closest papers by meaning
- UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence (NeurIPS 2026 · similarity 0.88)
- Tree of Preferences for Diversified Recommendation (NeurIPS 2025 · similarity 0.86)
- Enhancing Long-and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning (AAAI 2025 · similarity 0.85)
- Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models (AAAI 2025 · similarity 0.85)
- Long-Sequence Recommendation Models Need Decoupled Embeddings (ICLR 2025 · similarity 0.85)
- SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
