search

suanrong / SDNE

This is a implementation of SDNE (Structural Deep Network embedding)
http://www.kdd.org/kdd2016/subtopic/view/structural-deep-network-embedding
322 stars 119 forks source link

Embedding nodes after training? #17

Closed dzdang closed 5 years ago

dzdang commented 5 years ago

We are performing a link prediction on a paper citation network. We want to train on the citations from 1990-1997, and then predict links for papers after 1997. For example, we may want to predict links for papers in 1998.

To effectively do this, do we simply supply all the nodes from 1990-1998, and train on links from 1990-1997, and then perform link prediction? Or do we only supply nodes from 1990-1997, train on links from 1990-1997, and then somehow add the 1998 nodes into the embedding space after training? I believe the example in the SDNE paper does something like the former.

suanrong commented 5 years ago

I think both are ok. The nodes in 1998 without any link do not influence the model.