Anilkumar

Okay, thanks for suggestion. I forgot to mention that my graph is Fully connected(20 nodes), is this could be the reason, because all nodes might get the same representations. In...

so, that means I cannot use GCN, I would have to try Graph Attention networks or some other model which gives different representation?

Thanks for suggestion! I did use that but it does not generalize for different distribution(for eg. model trained with uniform distribution perform poorly on multi-variate gaussian distribution)

@buaacyw Did you manage to run the demo notebook successfully? I am getting the error https://github.com/hassony2/homan/issues/3#issue-1028295491 Did you also face this error?

I tried reducing the chunk size and the num of layers. But the error still persists. Besides, I do not have issues with gpu memory. If you are talking about...

but there is no number of labels involved as per my understanding

> It's hard to tell without knowing the exact config, but does this issue seem to help you? > #9 @krrish94 Here is more information about the error: Looks like...

@krrish94 Following the preview comment: I tried to print the tensors and found that values of tensor inds_g is too large and too small(which casuses out of bounds error) inds_g.min()...

More update: Actually these large values of indices are coming from func torchsearchsorted.searchsorted() inds = torchsearchsorted.searchsorted(cdf, u, side="right") --> after this line of code inds values are very extreme(out of...

> More update: Actually these large values of indices are coming from func torchsearchsorted.searchsorted() > inds = torchsearchsorted.searchsorted(cdf, u, side="right") --> after this line of code inds values are very...