Bug fix: `torch_sparse.transpose` outputs are coalesced

Graph-COM / GSAT

[ICML 2022] Graph Stochastic Attention (GSAT) for interpretable and generalizable graph learning.

https://arxiv.org/abs/2201.12987

MIT License

162 stars 21 forks source link

Bug fix: `torch_sparse.transpose` outputs are coalesced #3

Closed siqim closed 2 years ago

siqim commented 2 years ago

torch_sparse.transpose would coalesce outputs by default and mess up results when input edge_index is not sorted. This issue does not affect any reported results, but it may cause problems potentially. Setting coalesced=False resolves the issue.