gae
gae copied to clipboard
tkipf
Implementation of Graph Auto-Encoders in TensorFlow
Hi Thomas, I'm confused when you generate the negative edge labels of validation set as: ```python3 val_edges_false = [] while len(val_edges_false) < len(val_edges): idx_i = np.random.randint(0, adj.shape[0]) idx_j = np.random.randint(0,...
Hi Tomas, I am able to use gae on the small dataset(
Hi tkipf, thanks for your code! I have two questions about the data: 1. In the "input_data.py", why did you adjust the order of the test nodes features in the...
Hello! First of all thanks for this amazing work! I am Japanese, so I apologize if my English is not good. I want to embed a node in a graph...
Hi T. Kipf, Thank you for the great code. Is it also possible for you to share the function you used to produce the figure you show in the paper:...
I am trying to set up an environment to have the correct versions of necessary packages in Anaconda and the setup.py just installs the latest versions of packages. I am...
Hi @tkipf In preprocessing.py (line 77~96), **val_edges_false** seems have chance to be in **edges_all** when I run multiple times. It will trigger **assert ~ismember(val_edges_false, edges_all)** So, I guess the **if**...
Hi @tkipf Thanks for your work! It's awesome. But I still want to know how can I get the output graph? Becasue I want to get not only the result...
Hi @tkipf, Thank you for sharing the implementation. In the `OptimizerVAE` class, when defining the KL divergence, I think there is an (1/num_nodes)^2 term extra. One num_nodes comes in `(0.5...
Excuse me, the edges in the validation sets are the same for ten times, or the validation sets is randomly selected as in the code, only the proportion of the...
