Research map / Architectures and efficiency / RNNs and normalization
Hierarchical Context Enabled Recurrent Neural Network for Recommendation
Kyungwoo Song, Mingi Ji, Sungrae Park, Il-Chul Moon
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 bi-channel attention to HCRNN-3 (ablation) | HCRNN-3 · CiteULike | Recall@20: 25.42 -> 25.81 | Improved |
| Add bi-channel attention to HCRNN-3 (ablation) | HCRNN-3 · LastFM | Recall@20: 34.72 -> 34.80 | Improved |
| Add bi-channel attention to HCRNN-3 (ablation) | HCRNN-3 · MovieLens | Recall@20: 33.67 -> 33.83 | Improved |
| Add the HCRNN-2 interest-drift reset gate (ablation) | HCRNN-1 · CiteULike | Recall@20: 25.36 -> 25.10 | Hurt |
| Add the HCRNN-2 interest-drift reset gate (ablation) | HCRNN-1 · LastFM | Recall@20: 34.40 -> 34.14 | Hurt |
| Add the HCRNN-2 interest-drift reset gate (ablation) | HCRNN-1 · MovieLens | Recall@20: 33.78 -> 33.76 | No clear effect |
| Replace the HCRNN-2 reset-gate drift signal with a separate drift gate (ablation) | HCRNN-2 · CiteULike | Recall@20: 25.10 -> 25.42 | Improved |
| Replace the HCRNN-2 reset-gate drift signal with a separate drift gate (ablation) | HCRNN-2 · LastFM | Recall@20: 34.14 -> 34.72 | Improved |
| Replace the HCRNN-2 reset-gate drift signal with a separate drift gate (ablation) | HCRNN-2 · MovieLens | Recall@20: 33.76 -> 33.67 | No clear effect |
Closest papers by meaning
- ContextGNN: Beyond Two-Tower Recommendation Systems (ICLR 2025 · similarity 0.86)
- LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation (AAAI 2025 · similarity 0.86)
- SLMRec: Distilling Large Language Models into Small for Sequential Recommendation (ICLR 2025 · similarity 0.86)
- Dynamic Multi-Interest Graph Neural Network for Session-Based Recommendation (AAAI 2025 · similarity 0.85)
- Auto Encoding Neural Process for Multi-interest Recommendation (AAAI 2025 · similarity 0.85)
- MARS: Multi-resolution Adaptive Routing for Sequential Recommendation (NeurIPS 2026 · 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.
