-
I found the training time improvements of SGC vary on different datasets. For example, SGC was trained 28 times faster than GCN on Pubmed dataset, while it is only < 5 times faster than GCN on TWITTER…
-
Hi GNN Authors:
May I know how you use GNN for subgraph matching? I notice that there two files named "GNN_Subgraph" and "Net_Subgraph". Are these files for subgraph matching? By the way, can you i…
-
# Next paper candidates
Let's propose papers to study next! All papers mentioned in the comments of this issue will be listed in the next vote.
## Last session runner-up(s)
- [Graph Attention Ne…
-
# Next paper candidates
Let's propose papers to study next! All papers mentioned in the comments of this issue will be listed in the next vote.
## Last session runner-up(s)
- [Graph Attention Net…
-
I tired DynAE DynRNN and DynAERNN today and I found that,
when graphs[i-1] contains only part of nodes of graphs[i], there will be some broadcast error.
So, does this program requires that each gra…
wenjf updated
5 years ago
-
Hi,
I'm trying to study GAT, and awesome works!
I'm wondering how to understand "without ... depending on knowing the graph structure upfront", and "dropping all structural information".
I al…
-
# Next paper candidates
Let's propose papers to study next! All papers mentioned in the comments of this issue will be listed in the next vote.
## Last session runner-up
[Graph Attention Networ…
-
is this repo consists inductive and cross conformal prediction?
-
Is it possible to train the benchmarked DiffPool with no features? I just wanted to train on graph structure alone, and only have the edge_index and node and graph level outcome classes.
Right now …
-