snash4 / gat2vec Goto Github PK
View Code? Open in Web Editor NEWembedding attributed graphs
License: GNU General Public License v2.0
embedding attributed graphs
License: GNU General Public License v2.0
Can you use gat2vec to generate embeddings for datasets that are unlabeled? (i.e. no _label_10/30/50_na.adjlist files)
Hi,
I was going through the dataset you used for "Blog catalog". The dataset website has .mat file with four different kinds of information ( eg. Usercategory,usertag,tagnetwork,friendship).
The files being used by your model is _graph.adjlist for capturing graph structure and _na.adjlist for attributes of the nodes.
I couldn't find any relation between the data provided in the .mat file and the above two mentioned files which your model is using.
Could you please explain, how did you prepare this data ?
How do you generate structural and bipartite graphs?
I noticed that your repository doesn't have a license. Could you add one?
The accuracy is too low to match the accuracy in the paper
Excuse me, is there an experimental code for link prediction?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.