Questions tagged [graph-neural-network]

The tag has no usage guidance.

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

How to check consistency in a daata (graph) with MLP? [closed]

i read a paper where they use MLP to predict the degree of how likely the assertion (information) it is possible?
0
votes
0answers
14 views

HinSAGE link existence prediction?

From the demo of HinSAGE link prediction I’ve understood that the model can predict the label of a link between two nodes. I’m looking to know if a link should be existing (binary). For example, let’s ...
0
votes
0answers
10 views

What is the contraction map constraint in the context of Graph Neural Nets?

In this paper https://arxiv.org/pdf/1511.05493.pdf (GATED GRAPH SEQUENCE NEURAL NETWORKS,2016), it is stated that in a Graph Neural network initialising hidden states is not required, as 'In GNNs, ...
0
votes
0answers
7 views

Term Weighting on Graph Convolutional Networks

i have read paper about graph convolutional networks https://arxiv.org/abs/1609.02907 since it a document classification task, is it important to choose term weigthing method like tf-idf. the default ...
0
votes
0answers
31 views

What are the differences between Knowledge Graph Embeddings (KGE) and Graph Neural Network (GNN)

From page 3 of this paper Knowledge Graph Embeddings and Explainable AI, they mentioned as below: Note that knowledge graph embeddings are different from Graph Neural Networks (GNNs). KG embedding ...
0
votes
0answers
11 views

Multiple sizes and types of Inputs for a NN

I have multiple inputs for a Neural Network and a regression problem. The first input is a Adjacency matrix, the two other are one hot encodings(or binary). I am using the Flatten layer for each of ...
0
votes
0answers
7 views

Is there any inductive Graph Variational Auto Encoder?

I have been reading about how we can model a Variational AutoEncoder (VAE) into a Graph Variational AutoEncoder (GVAE) where the decoder reconstructs the adjacency matrix. I presume that this approach ...
2
votes
1answer
36 views

Knowledge Graph as an input to a neural network

I want to create a neural network that takes as an input a knolwedge subgraph(different types of nodes and different types of edges) to predict some properties. For instance an input in the graph can ...
0
votes
0answers
17 views

Graph Neural Network - Node and Global Properties

I am trying to work with Graph neural networks. I am trying to use the 3d coordinates and some othe things related to those positions as features. However the whole system also has some global ...
1
vote
0answers
53 views

Isn't graph embedding a step back from non-euclidean space?

As I understand, we use graph embedding to make a euclidean representation of non-euclidean structure - graph. Does it mean that conceptually we just take a step back to, may be, more complex, but ...
0
votes
0answers
51 views

Tensorflow dtype=resource

I have created a tensor: ...
1
vote
1answer
39 views

How does graph classification work with graph neural networks

I am reading the paper The Graph Neural Network Model by Scarselli et al. I understand how node classification works. I am having trouble understanding how graph classification works however. In ...
0
votes
0answers
5 views

Deep Graph tutorial, visualization not displaying

I am following this Deep Graph tutorial to learn more about GNNs. In the last step, they create a visualization of the network training, using the following code: ...
1
vote
1answer
72 views

What is difference between transductive and inductive in GNN?

It seems in GNN(graph neural network), in transductive situation, we input the whole graph and we mask the label of valid data and predict the label for the valid data. But is seems in inductive ...