Research map / Graph learning / Knowledge and temporal graphs
Multifaceted Scenario-Aware Hypergraph Learning for Next POI Recommendation
Yuxi Lin, Yongkang Li, Jie Xing, Zipei Fan
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 adaptive parameter splitting (ablation) | MSAHG · NYC | ACC@1: 0.2026 -> 0.2268 | Improved |
| add scenario-specific sub-hypergraphs (ablation) | MSAHG · NYC | ACC@1: 0.2164 -> 0.2268 | Improved |
| add adaptive parameter splitting (ablation) | MSAHG · NYC | MRR: 0.3392 -> 0.3721 | Improved |
| add scenario-specific sub-hypergraphs (ablation) | MSAHG · NYC | MRR: 0.3592 -> 0.3721 | Improved |
| use scenario-aware MSAHG instead of DCHL | MSAHG · NYC (Tourist scenario) | ACC@1: 0.1029 -> 0.1921 | Improved |
| use scenario-aware MSAHG instead of DCHL | MSAHG · NYC (Weekend scenario) | ACC@1: 0.0977 -> 0.1868 | Improved |
| use MSAHG instead of GETNext in some scenarios | MSAHG · TKY (Local scenario) | ACC@20: 0.6247 -> 0.5910 | Hurt |
| overall MSAHG vs baselines across scenarios | MSAHG · Gowalla, NYC, TKY | all metrics: 48/90 best, 30/90 second | Mixed |
| add splitting and sub-hypergraphs (ablation) | MSAHG · NYC | train memory (MB): 697.66 -> 1,292.36 | Hurt |
| add splitting and sub-hypergraphs (ablation) | MSAHG · NYC | train time per epoch (s): 10.26 -> 10.69 | No clear effect |
| MSAHG vs STHGCN training speed | MSAHG · NYC | train time per epoch (s): 73.29 -> 10.69 | Improved |
Closest papers by meaning
- TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation (AAAI 2024 · similarity 0.88)
- Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation (AAAI 2024 · similarity 0.86)
- GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space Model (AAAI 2025 · similarity 0.86)
- Integrating Personalized Spatio-Temporal Clustering for Next POI Recommendation (AAAI 2025 · similarity 0.85)
- Enhancing Long-and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning (AAAI 2025 · similarity 0.85)
- SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation (NeurIPS 2025 · similarity 0.84)
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.
