Comments (3)
Ok, thanks a lot. I will choose to post this question under pyg. If I have any update, I will let you know!
from graphgps.
Hello Tianyu,
Thanks for pointing out the PyG implementation, I was not aware of it! However, you have to raise any issues regarding PyG at PyG github repo.
What do you actually mean by "I wonder why it does not have the size of output channel? I think in the paper it mentioned that the model will update the dimensions of embeddings."? From a quick look at their code, what pops up to me is that they are not supporting MPNNs that update edge embeddings, unlike the official GPS implementation here.
Best,
Ladislav
from graphgps.
Hi Ladislav, if my understand is correct, could we use GPSConv like:
import torch
from torch.nn import Module, Linear
from antisymmetric_conv import GPSConv
from torch_geometric.data import Data
class GPS(nn.Module):
def __init__(self,
input_dim, output_dim, hidden_dim, ) -> None:
super(GPS, self).__init__()
self.input_dim = input_dim
self.output_dim = output_dim
self.hidden_dim = hidden_dim
self.phi = phi
self.num_iters = num_iters
self.epsilon = epsilon
self.gamma = gamma
self.act = act
self.act_kwargs = act_kwargs
self.bias = bias
self.emb = nn.Linear(self.input_dim, self.hidden_dim)
self.conv = GPSConv()
self.readout = nn.Linear(self.hidden_dim, self.output_dim)
def forward(self, data: Data) -> torch.Tensor:
x, edge_index, edge_weight = data.x, data.edge_index
x = self.emb(x)
x = self.conv(x, edge_index)
x = self.readout(x)
return x
I can update the embeddings directly.
from graphgps.
Related Issues (20)
- Graph generation HOT 3
- Cannot launch experiments for some datasets (PATTERN/CLUSTER/Peptides-func/Peptides-struct) HOT 3
- Question about maxfreqs HOT 1
- Implementing on our custom dataset HOT 1
- Feature Request: Caching of Precomputed Encodings HOT 1
- Implementation on custom dataset HOT 1
- mismatch shape on inference HOT 1
- Is there a vanilla implementation without graphgym HOT 1
- How to implement graphgps to node classification HOT 2
- AttributeError: 'NoneType' object has no attribute 'mem' HOT 3
- Where can I download pretrianed ckeckpoints for inference? HOT 1
- BUG: adding graphormer graph token breaks node permutation invariance HOT 3
- question about computational complexity in global-attn HOT 1
- Concerns about time consumption of function graphormer_pre_processing() HOT 1
- Where is the "batch.node_label_index" property set HOT 1
- Test ACC for PPA dataset HOT 2
- Link broken for PCQM-Contact HOT 1
- AssertionError: Invalid type <class 'NoneType'> for key layer_edge_indices_dir; valid types = {<class 'tuple'>, <class 'int'>, <class 'float'>, <class 'bool'>, <class 'list'>, <class 'str'>} HOT 1
- ValueError: 'cfg.optimizer_config' undefined
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from graphgps.