muhanzhang
commented
3 years ago Hi, you don't need to call the "runpred{}.sh". You can just do BO experiments normally following the README, and then "python summarize.py" will print the rmse and pearson's r values of each model and save them in "bayesian_optimization/**_aggregate_results/output.txt".
The predictive performance is just gotten from the first BO iteration (i.e., use the trained sparse GP in the first iteration to evaluate on the test graphs).
Could you please give more details about how to reproduce Table 2 in the paper? The repository contains train commands for the models and scripts for the Bayesian optimization. But for the Table 2 experiments, it seems that SGP has to be trained differently? There is the following option in the bo.py code, but I do not find the sh file. Thank you already!
if args.predictor: copy('runpred{}.sh'.format(data_type), save_dir)