3
$\begingroup$

Is there any precedent for DL use of pretrained graph embeddings in a similar manner to word embeddings?

$\endgroup$
1
$\begingroup$

As far as I understand the topic embeddings are not portable between graphs since every graph has their own characteristics which you need to learn. At the field of word embeddings, it is different since domain stays the same (words).

In the field of graphs, you usually train the model on the same graph that will be embedded later. It is also important to train on the same graph because the labels of nodes are usually nodes IDs which are graph specific. In the field of words embeddings, the method recognizes words by their name (sequence of letters) while in graphs nodes are recognized by their IDs.

Hope that it explains a bit. If you want to understand graph embeddings, in general, I suggest reading this story.

| improve this answer | |
$\endgroup$
1
$\begingroup$

There are a few. The most popular one is probably the embedding that Facebook Research team made using their Pytorch Big Graph (PBT) on the entire Wikipedia content. The pretrained embedding is very large in terms of the number of nodes/topics and also file size (30+GB gzip file!)

| improve this answer | |
$\endgroup$
0
$\begingroup$

Am you actually looking for graph neutral network?

Note that most (popular) graph embedding algorithms are unsupervised learning, in that sense it does not make too much sense of getting a "pre-trained model".

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.