Graph networks as learnable physics engines for inference and control
Open paper
Benchmark
Model
Rank
Results
weather-forecasting-on-sd
GN-skip
#9
MSE (t+1): 0.6543 ± 0.1195
MSE (t+6): 0.9872 ± 0.2425
weather-forecasting-on-sd
GN-only
#10
MSE (t+1): 0.7007 ± 0.0848
MSE (t+6): 1.0422 ± 0.0673
Rank counts only results with a code link.