issues
search
JHL-HUST
/
NAGphormer
NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs
Apache License 2.0
115
stars
15
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to achieve reasoning on large-scale graph-level tasks
#9
Jedges
closed
4 months ago
3
Sorry to ask again, where is the connection between the feature matrix X and the structure matrix U in your paper (Equation 10) embodied in this code?
#8
phoebe11111111
closed
6 months ago
1
Hi! What part of the code represents the structure matrix U?
#7
phoebe11111111
closed
6 months ago
2
为什么在idx_train,idx_val和idx_test里面cora数据集的划分变成了1626:542:540，原来的划分不应该是120:500:1000吗？
#6
fosLIANG
closed
11 months ago
1
How do you implement the graphGPS to node classification task?
#5
OswaldoBornemann
opened
1 year ago
0
Preprocess data and make split
#4
kaansancak
closed
8 months ago
0
Unable to reproduce the results
#3
kaansancak
opened
1 year ago
3
splits for CoraFull, CS and Physics
#2
SiyuanHuangSJTU
opened
1 year ago
1
Looking forward the code~
#1
codeinging
closed
1 year ago
0