-
Notifications
You must be signed in to change notification settings - Fork 833
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Number nodes at each layers #13
Comments
If I understand your question correctly, the way it works is:
Does that make sense? |
yes, and it's seem to me that it is different from what I read in the paper. |
Hi, Yes the sampling can be a bit counter-intuitive and we tried to clear this up in the newest arxiv version. The description by @bkj is correct. Hopefully the new arxiv minibatch description is more clear, as it directly matches @bkj's description. Apologies for the confusion! In general, we (and other researchers) have found that increasing the neighborhood sample size improves performance but that the performance quickly plateaus by around 25-50 neighbors. This general trend holds for a number of datasets and has been replicated in a couple ICLR submissions. Of course, in a network with extremely high average degree or atypical degree distribution things might be different, but right now this is an empirical question and so far, we have found that the model can achieve near optimal performance with <50 sampled neighbors across all datasets tested. In future work, we hope to characterize this tradeoff more formally with regards to graph properties, such as density and clustering. |
Thank you for your answers. I'm really fascinated by your work and hope to see the new arxiv version. |
In the unsupervised model, I notice that it use the second layers's num_samples as the number of neighbor nodes for the first layers. This lead to samples shape for next aggregate function become this:
These line:
https://github.com/williamleif/GraphSAGE/blob/master/graphsage/models.py#L268-L275
https://github.com/williamleif/GraphSAGE/blob/master/graphsage/models.py#L299
https://github.com/williamleif/GraphSAGE/blob/master/graphsage/models.py#L326-L327
Thank you, I learned a lot from the code
The text was updated successfully, but these errors were encountered: