Questions tagged [pytorch-geometric]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
4 views

RGCN using source and targets of edges for aggregation

I am checking an old TF v1 repository (https://github.com/microsoft/tf-gnn-samples) and trying to do the same thing in PyG. I see RGCN implementation has an option that says if it should get only ...
tsadigov's user avatar
0 votes
0 answers
8 views

PyG Autoencoder reconstruction loss criterion node vs link prediction

In link_pred.py they use this criterion in computing the loss (which is like what we used in SRP). criterion = torch.nn.BCEWithLogitsLoss() https://github.com/pyg-...
sAguinaga's user avatar
  • 121
0 votes
0 answers
177 views

PlotNeuralNet plot interpretation

I am new to machine learning, I know how to build a simple neural network, but I don't know how to visualize my model accurately. PlotNeuralNet is really an amazing ...
Tianjian Qin's user avatar
1 vote
1 answer
79 views

What're the standard ways of padding data for GNNs?

I am working on materials property prediction using GNNs with torch_geometric. Each data in my dataset has different number of feature vectors x, edge_index vectors ...
user174967's user avatar
1 vote
1 answer
87 views

Trouble Training GNN for Binary Node Classification Task

I am using a GNN to solve a problem in which I have a query target and an undirected graph. My goal is to emit a subset of nodes in the graph (via a node-wise binary prediction) whose features sum to ...
mt_'s user avatar
  • 11
1 vote
0 answers
221 views

What is the standard way to incorporate a mask in a custom pytorch geometric dataset?

I am using pytorch geometric, and I need to create several masks for different experiments. I am creating a mask in the process function of my dataset class. Here ...
Ralff's user avatar
  • 123
0 votes
0 answers
114 views

How to implement edge feature in message passing algorithm of Pytorch Geometric?

I am trying to implement a custom message passing function $ x^k_i = x^{k-1}_i + m^k_i$ where $x_i$ is the node embedding of the i'th node and $m^k_i$ is the message getting delivered at the i'th node ...
Formal_this's user avatar
1 vote
1 answer
2k views

Is it possible to combine models in pytorch and pytorch geometric?

I am working on a node classification problem with graphical data. I've used PyTorch to classify nodes by simply applying a network to the individual nodes (e.g., ignoring graphical structure), and I'...
Ralff's user avatar
  • 123
0 votes
0 answers
311 views

My model is not learning

I am using the ogb molhiv dataset for graph classification, I imported the data and created the DataLoader following the ogb documentation. The data is composed of 41127 graphs and there are 2 classes....
edak's user avatar
  • 3
1 vote
1 answer
301 views

Captum vs GNNExplainer for explainability in Graph Neural Networks

I'm new to Graph Neural Networks and interested in exploring frameworks that allow the identification of nodes/edges that underlie prediction. I came across : (1) a model architecture (GNNExplainer) ...
batlike's user avatar
  • 111
1 vote
0 answers
164 views

Dying gradient issue in Graph Neural Networks

I am using Pytorch-Geometric library to implement a Graph Convolutional Layer(GCN) followed by few linear layers for a prediction task. But after training on graphs with np. of nodes being 10K and no. ...
Kooled's user avatar
  • 11
0 votes
2 answers
721 views

How to apply Geomertic mean in python

I am trying to built a function to calculate the Geometric mean for Growth column and Avg_growth. Year Company Name FH_PBIDT ...
HARI's user avatar
  • 1
0 votes
0 answers
35 views

Weird train and validation curves

I would like to train a GCN for protien-ligand binding affinity regression. I use GCNConv from pytorch geometric, ReLU for all activations and Dropout (0.2) after 2 dense layers each. Using ReLU for ...
Nurlybek Amangeldiuly's user avatar
6 votes
1 answer
2k views

What is the difference between FC and MLP in as used in PointNet?

I am trying to understand the PointNet network for dealing with point clouds and struggling with understanding the difference between FC and MLP: "FC is fully connected layer operating on each ...
EddyWD's user avatar
  • 197
3 votes
1 answer
279 views

Graph Embedding Vs Graph Convolution Network

I'm new in Graph-Embedding and GCN(Graph/Geometric Convolution Network). I'm confused and not very much sure about "How training works in GCN"? As per my understanding, GCN training data will be ...
vipin bansal's user avatar
  • 1,262
1 vote
1 answer
5k views

What does the collate function in pytorch (geometric)?

I am creating a message passing neural network and have some issues with the dataset creation. In pytorch (geometric) it is recommended to create a dataset with the following class. I wonder what is ...
Soerendip's user avatar
  • 724
8 votes
2 answers
4k views

How to use Graph Neural Network to predict relationships between nodes with pytorch_geometric?

Let's say I have a partly connected graph that represents members of many unrelated communities. I would like to predict the possible friendships between members of the same community: on an sliding ...
Soerendip's user avatar
  • 724