Spatio-temporal Prediction on Milan-SMS 10% (train)
0.7324NRMSEST-Vision-LLM
Evaluation Results
| Method | Links | |
|---|---|---|
| ST-Vision-LLMInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.7324 | |
| GCNGPTInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.8575 | |
| GATGPTInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.8679 | |
| ST-LLMInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.8901 | |
| STNInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.9223 | |
| Time-LLMInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.9315 | |
| ResLSTMInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 0.9412 | |
| GWNETInput sequence length (S)=12, Prediction horizon (K)=36, Few-shot training percentage=10%2025.10 | 1.1417 |