Skip to main content
Stack Overflow
  1. About
  3. For Teams
Filter by
Sorted by
Tagged with
0 votes
0 answers
29 views

I'm having a lot issues implementing shap plot for my SGC model. Any one experienced the problem the same problem ,can give an example. The problem is that there are a lot errors when try shap with ...
1 vote
0 answers
65 views

I have a dataframe representing a point cloud plus node data: I have hence X,Y,Z positions as well as "node features". I would like to represent it as a graph to use it in a GNN. I would ...
1 vote
1 answer
77 views

I have created this data: HeteroData( user={ x=[100, 16] }, keyword={ x=[321, 16] }, tweet={ x=[1000, 16] }, (user, follow, user)={ edge_index=[2, 291] }, (user, tweetedby, tweet)={ ...
1 vote
0 answers
47 views

I am comparing pairs of identical directed graphs represented in GXL format using the Graph-Matching-Toolkit(https://github.com/dzambon/graph-matching-toolkit). Since the graphs are identical, I ...
0 votes
1 answer
63 views

I am trying to model an autoencoder of a graph data to best reconstruct the graph but Im facing an issue when trying to do the training. I created the graph tensor as follows: edge_sources = ...
1 vote
0 answers
238 views

I’m currently engaged in a project that involves the construction of a Graph Neural Network (GNN) model using PyTorch Geometric. The primary objective of this project is to predict train delays in the ...
0 votes
0 answers
256 views

I am trying to create a classification algorithm using Graph Neural Networks (GNNs) in Python, but I am encountering an error that I can't resolve. I have already tried removing NaN values from my ...
0 votes
0 answers
25 views

I have locally created an instance of a custom dataset. So my question is can i save to dataset locally so that i can use it later. The dataset contains 5000 graph instances. I have tried the ...
0 votes
1 answer
48 views

In my customized dataset there are only feature matrices and adjacency matrices.The feature matrix is a ×ばつ3000 one-dimensional tensor,and edge_index is torch.Size([2, 18708]) My code is : from ...
1 vote
1 answer
200 views

I have a graph convolution model built and wanted to implement a custom unsupervised loss function like the one shown in below picture: Where yv is the learned embedding of a node v and rand denotes ...
0 votes
1 answer
130 views

I'm new to pytorch and pytorch geometric and I'm trying to do node classification. About 5-10% of the nodes should be classified as violates (as they violate a condition that I want to predict), while ...
0 votes
0 answers
36 views

I would like to add a GCN layer with a given adjacency matrix at the beginning of a 1D convolutional autoencoder. It seems for the 1DCNN each batch of data is of dimension (batch_size, number_features,...
2 votes
0 answers
112 views

I try to set up Differential Private learning on a Graph Temporal Neural Network, using opacus for the differential privacy and A3TGCN2 from the pytorch-gemoemtric-temporal library for the TemporalGNN ...
0 votes
1 answer
68 views

I am running a program to construct a heterogeneous graph and then calculating the network indicator of the pointed node using NetworkX. However, in the output Excel file, the column for the pointed ...
0 votes
1 answer
255 views

I am working on a fraud detection project using GNN. My graph has banking codes (SWIFT BIC codes) as nodes and the edges represent transactions. Below are the shapes of my tensors: Node Features ...

15 30 50 per page
1
2 3 4

AltStyle によって変換されたページ (->オリジナル) /