Hottest 'graph-neural-network' Answers

2

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 contain a simplified representation of the input data (i.e. summary of key features), which can be used to reconstruct the output. If we take a dictionary ...

answered Feb 28 '21 at 15:09

WBM

6675 silver badges16 bronze badges

2

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 training.

neural-network deep-learning gnn graph-neural-network

answered May 6 '20 at 8:13

DunkOnly

5314 silver badges13 bronze badges

1

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 transductive learning, where the test data(nodes here) is seen (without knowing the labels) during training. What you might have in mind is inductive learning(train set ...

training graph-neural-network inference

answered Oct 17 '21 at 17:22

Sēbastian

1262 bronze badges

1

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 they started. Node embeddings are like that. You take the information of neighbourhood nodes and combine it with the information in the original node. The art ...

neural-network cnn graphs graph-neural-network

answered Feb 25 '21 at 11:45

Abhishek Verma

6241 silver badge3 bronze badges

1

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 algorithm. However, maybe by definining a 'cost function' that you want to optimize (minimize or maximize) you can convert it to a supervised learning task. ...

machine-learning machine-learning-model graphs graph-neural-network

answered Oct 29 '20 at 6:30

YAS

111 bronze badge

1

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 the relationship, the second dimension is for the relation type, and the third dimension is for the node on the right side of the relationship. Then you can ...

neural-network graph-neural-network knowledge-graph

answered Jul 22 '20 at 14:54

zachdj

2,1614 silver badges11 bronze badges

Stack Exchange Network

current community

your communities

more stack exchange communities

Tag Info

Hot answers tagged graph-neural-network