qitianwu/NodeFormer
The official implementation of NeurIPS22 spotlight paper "NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification"
Jupyter NotebookMIT
Issues
- 1
how to get the latent graph structure
#23 opened by bwrooney82 - 1
I have a list of graphs on which I want to perform node classification task. Each graph has nodes, node attributes, edges and associated labels for each node. Any guidelines on how to train this dataset?
#18 opened by clydebailey - 0
Runtime error when running main-batch.py
#22 opened by vickychen928 - 5
- 2
Clarification on Visualization Techniques for Graphs 4 and 7 under Linear Complexity Constraints
#21 opened by FarisXiong - 2
Deezer Europe Dataset on SGFormer/NodeFormer
#19 opened by ryandeng1 - 1
Same results for the last four runs
#17 opened by null-xyj - 1
- 1
Regarding DGL Implementation
#15 opened by jweihe - 1
ValueError: Both 'src' and 'index' must be on the same device (got 'cpu' and 'cuda:1')
#13 opened by xx-m - 1
- 1
- 1
What is the principle of exchanging the first two dimensions when calculating QKV attention?
#10 opened by WithMeteor - 5
Reproducing results on Deezer dataset
#3 opened by Chenhui1016 - 1
Code without inductive settings????
#9 opened by tony-wl - 9
- 4
Accurate scores of Figure 2 in the paper
#6 opened by AimeJiayue - 3
- 4
the training code for the GCN, SGC models on the ogbn-proteins and amazon2m datasets
#5 opened by SiyuanHuangSJTU - 2
- 2