Research map / Image generation / Autoregressive and latent generation
GeoGen: A Two-stage Coarse-to-Fine Framework for Fine-grained Synthetic Location-based Social Network Trajectory Generation
Rongchao Xu, Kunlin Cai, Lin Jiang, Zhiqing Hong, Yuan Tian, Guang 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 |
|---|---|---|---|
| use interpolation for latent movement reconstruction vs replication (ablation) | S2TDiff · FS-NYC | Distance JSD: 0.084 -> 0.079 | Improved |
| use interpolation vs fixed central point (ablation) | S2TDiff · FS-NYC | Distance JSD: 0.097 -> 0.079 | Improved |
| add S2G Attention module (ablation) | S2TDiff · FS-NYC | Interval JSD: 0.080 -> 0.067 | Improved |
| add dynamic context fusion (ablation) | Coarse2FineNet · FS-NYC | Radius JSD: 0.138 -> 0.065 | Improved |
| increase coarse interval from 2 to 6 hours (ablation) | GeoGen · GW-STO | Distance JSD: 0.454 -> 0.073 | Improved |
| increase coarse interval from 2 to 12 hours (ablation) | GeoGen · GW-STO | Interval JSD: 0.292 -> 0.444 | Hurt |
| increase coarse interval from 2 to 6 hours (ablation) | S2TDiff · GW-STO | S1 memory (GB): 2.36 -> 0.35 | Improved |
| GeoGen vs ControlTraj | GeoGen · FS-TKY | fidelity JSD average: 0.140 -> 0.065 | Improved |
| GeoGen vs best baseline for utility | GeoGen · FS-NYC | RMSE: 0.321 -> 0.225 | Improved |
| GeoGen vs MoveSim on spatial utility | GeoGen · FS-TKY | ED: 16.90 -> 15.82 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DiffTraj — DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model (NeurIPS 2023) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation (AAAI 2024 · similarity 0.85)
- GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space Model (AAAI 2025 · similarity 0.85)
- Integrating Personalized Spatio-Temporal Clustering for Next POI Recommendation (AAAI 2025 · similarity 0.83)
- Generative Human Trajectory Recovery via Embedding-Space Conditional Diffusion (ICML 2025 · similarity 0.83)
- Holistic Semantic Representation for Navigational Trajectory Generation (AAAI 2025 · similarity 0.83)
- Cross-Domain Trajectory Association Based on Hierarchical Spatiotemporal Enhanced Attention Hypergraph (AAAI 2025 · similarity 0.83)
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.
