About different results running the same code

[zhandand]

Though I have fix the seed, the results after running the same code are different. Do u have any ideas about that?
` random.seed(0)

np.random.seed(0)
torch.manual_seed(0)
torch.cuda.manual_seed_all(0)    
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False`

[zhandand]

I am wondering if this could answer my question.

[SXKDZ]

Thanks for your interests. Your referred information is correct. That has something to do with PyG's side. You need to convert the sparse adjacency matrix to adj_t type. Please refer to their tutorial on the randomness in experiments.