PageRank centrality computed by this codes maybe meaningless

[c747903646]

drop weightis is computed according to the folllowing codes in pGRACE/functional.py :

`def pr_drop_weights(edge_index, aggr: str = 'sink', k: int = 10):
pv = compute_pr(edge_index, k=k)
pv_row = pv[edge_index[0]].to(torch.float32)
pv_col = pv[edge_index[1]].to(torch.float32)
s_row = torch.log(pv_row)
s_col = torch.log(pv_col)
if aggr == 'sink':
s = s_col
elif aggr == 'source':
s = s_row
elif aggr == 'mean':
s = (s_col + s_row) * 0.5
else:
s = s_col
weights = (s.max() - s) / (s.max() - s.mean())

return `

However, in debugging codes, I found that some elements in array pv could be 0 (while using WikiCS for training). After executed torch.log(), min value of s_row and s_col will be -inf, resulted in all of weights became 0. At that time, the weights was meaningless.

[SXKDZ]

Hi thanks for your question! We find that some nodes in the WikiCS do not have incoming edges. Therefore we slightly change the computation from edge centrality to removal weights as follows 𝑠_𝑒 = log(𝑤_𝑒 + 1) to avoid zero values when there are no incoming edges in directed graphs. Empicially we find that such a modification has no obvious impact to the performance. We will upload a new version to arXiv very soon.