graphtransformer

graphtransformer copied to clipboard

Do you plan to apply `graphtransformer` to a machine translation task?

2

Would be interested to know whether you plan to apply the `graphtransformer` for a machine translation task in the future?

nashid

Why did you divide this term?

1

Hi there, I was reading your code on graphtransformer, I'm kind of curious on the operation shown below. Why did you divide the wV score by the w(or so called...

sperfu

checkpoints of pretrained models

1

Hello, Thanks for sharing this amazing work! Any chance you can share the pretrained models used in the paper ? Thanks!

AmeenAli

Memory consumption

1

Could you provide some additional information about the memory consumption using your Graph Transformer? You state, that sparse-attention favors both computation time and memory consumption, but do not provide actual...

GregorKobsik

There's a series of numbers in 'train.index', but i don't know how to explain it

fengbaoyihao3000

g.send_and_recv(eids, fn.src_mul_edge('V_h', 'score', 'V_h'), fn.sum('V_h', 'wV')) this only update target node; head_out = g.ndata['wV']/g.ndata['z'] so this only update target node;the source node not update?

zhouxiaozhang

```python net_params['in_dim'] = torch.unique(dataset.train[0][0].ndata['feat'],dim=0).size(0) # node_dim (feat is an integer) #code in main ...... in_dim_node = net_params['in_dim'] # node_dim (feat is an integer) #graphtransformer/nets/SBMs_node_classification/graph_transformer_net.py line:19 ...... self.embedding_h = nn.Embedding(in_dim_node, hidden_dim)...

Win7ery

# Add Python Testing Infrastructure ## Summary This PR sets up a comprehensive testing infrastructure for the Graph Transformer project. While the project uses Conda for its main dependencies, I've...

llbbl