3
votes
Accepted
What is difference between transductive and inductive in GNN?
In inductive learning, during training you are unaware of the nodes used for testing. For the specific inductive dataset here (PPI), the test graphs are disjoint and entirely unseen by the GNN during ...
2
votes
What are latent representations?
The latent representation is the simplified model of your input data, for example, created by a neural network.
Considering an autoencoder, the central layer of this network (after training) will ...
2
votes
Accepted
How to perform inductive train/test split for GraphSAGE classification
If I understood you correctly, you are looking to do a kind of stratified sampling, and would like to create the strata or clusters to perform train/ test splits over the identified "highly ...
2
votes
How to perform inductive train/test split for GraphSAGE classification
I don't have a tone of experience in graph based ML applications, so correct me if I'm oversimplifying, but to restate the problem:
You have a graph of weakly connected nodes
You want to use ...
2
votes
How to perform inductive train/test split for GraphSAGE classification
One option would be using an existing package that is designed to train/test split graphs while maintaining class rates. For example, the PyG (PyTorch Geometric) package has RandomNodeSplit class ...
1
vote
Accepted
Normalizing softmax by dividing by its maximum?
You are not missing, the text seems to miss explanation. The important takeaway is how do use Fuzzy logic where embedding values are nearly same for two classes.
The example discussed:
h1 =[-1.2,2.3]...
1
vote
How to perform inductive train/test split for GraphSAGE classification
If you are using Pytorch geometric library, checkout https://pytorch-geometric.readthedocs.io/en/latest/modules/loader.html?highlight=ClusterData#torch_geometric.loader.ClusterData, it cluster data in ...
1
vote
Accepted
How train - test split works for Graph Neural Networks
Does the algorithm consider as neighbourhood only the green nodes(test
set) or it also considers the blue node's?
It does consider both blue nodes and green nodes.
Note tha GNN deals with ...
1
vote
Understanding Node Embeddings
First, let me give you an intuitive explanation. When you drop a pebble in water, you see the ripples being formed. Imagine that in reverse. All those ripples comes together at the point from which ...
1
vote
From Labels to Graph: what machine learning approaches to use?
Your graph is characterized by a set of nodes and edges. It means given a start point x, show me the next node z1, then from z1 show me z2 and so on. This looks like the definition of graph-searching ...
1
vote
Knowledge Graph as an input to a neural network
You can represent this type of knowledge graph as a binary $n \times r \times n$ tensor. (You can think of this as a 3D matrix if it helps.)
The first dimension is for the node on the left side of ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
graph-neural-network × 48deep-learning × 13
graphs × 10
machine-learning × 9
neural-network × 8
embeddings × 6
python × 4
tensorflow × 4
convolutional-neural-network × 4
cnn × 3
pytorch × 3
knowledge-graph × 3
gnn × 3
classification × 2
keras × 2
machine-learning-model × 2
training × 2
recommender-system × 2
word-embeddings × 2
evaluation × 2
transformer × 2
r × 1
regression × 1
predictive-modeling × 1
random-forest × 1