You would first need to split your data variable into an X variable containing the features you want to use and a y variable that contains the value you are trying to predict. After this you can use train_test_split to split the data into a training and test dataset. Combining these two steps would look something like this:
import pandas as pd
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 ...
Hard to tell. Usually you would expect some difference between the two, and you would worry if they have dissimilar shapes. But yours are very similar, and the validation curve has a smaller loss from the start, compared to the training loss. Maybe the training/validation split was just unfortunate. Try to train the model again with a new validation sample, ...
It looks like overfitting. Check this article to learn about interpreting different types of learning curves. TensorFlow also has a tutorial on this topic. There is a clear split between the curves at about epoch 10 where training keeps learning at a much faster rate compared to validation.
But as you point out validation loss stays pretty much stable with ...
The answer is in the question :)
Only human eyes can judge of the readable character of a text, its creativity, its grammatical correctness etc.
In the example of a model trained on Shakespeare's writing, take a group of human annotators (preferably literature experts) and ask them to annotate texts as likely authored by Shakespeare or not (variant: mark ...
Do not I repeat DO NOT use full dataset for any kind of Machine learning purposes. Always split your data into train, valid and test sets before proceeding with your model creation. Even if the dataset is small, always split it. The ratio you choose is up to you (usually when the dataset is small, you choose 85:15 or 90:10 ratio but again it is up to you).
There are two options:
A pass through network with direct connections with a weight of 1. The activations of the input nodes in would be the same as the activations of the out nodes.
Autoencoder - An autoencoder learns the encoding of data, in this case no encoding.