search

danielzuegner / netgan

Implementation of the paper "NetGAN: Generating Graphs via Random Walks".
https://www.kdd.in.tum.de/netgan
MIT License
191 stars 67 forks source link

How to train the ERGM model mentioned in your paper? #5

Open xiangsheng1325 opened 3 years ago

xiangsheng1325 commented 3 years ago

Hi, thanks for your excellent work on graph generation.

I have some problems during the implementation of the baseline method ERGM in your paper. I followed your parameter settings in R, but the simulation results are always bad (such as the explosion of the number of edges).

This is my R code for graph simulation by ERGM: result.network <- simulate( ergm( input.network ~ edges + degcor + degree1.5 + gwesp + density, control=control.ergm( MCMLE.maxit=20, MCMLE.density.guard=100000, parallel=2, parallel.type="PSOCK" )) ) where 'input.network' is the graph to be simulated, and the function 'simulate' is from package 'ergm'. I wonder how to have the right hyper-parameters to have the best simulation result like your paper's.

xiangsheng1325 commented 3 years ago

I have tested several datasets and I find that ERGM can successfully simulate molecule graphs. However, simulation cannot converge when generating big graphs (having more than 500 nodes).