Giannis Nikolentzos

Hi @happysnzy , This has been discussed in the past. See this: https://github.com/ysig/GraKeL/issues/37

Hi @anonymous-author-here , I tried to reproduce the error, but I could not. Have a look here: https://colab.research.google.com/drive/16dLHV-4vksiid80ryMxDlRCjHlAwOXV3?usp=sharing Which version of GraKeL have you installed?

Hi @JuliusSchwartz , Thank you for spotting these issues and letting us know. Indeed you are right. We will fix them in the next version.

Hi @saiprasanna06 , You can use the following code. ``` import numpy as np from scipy.sparse import csr_matrix,lil_matrix from grakel import Graph has_node_labels = True graph_indicator = np.loadtxt("own_dataset_graph_indicator.txt", dtype=np.int64) _,graph_size...

Hi @hkmztrk, To my understanding, you mean a hierarchical approach where sentences are represented as sets of word embeddings and mapped into vectors, and then documents are represented as sets...

Hi @snnpzz , For the code to be adapted to the task of node classification, no readout function need to be applied. Thus, the `forward()` function in the model.py file...

Hi @cwsy , Thanks for your interest in our work. In our experiments, we only used a single iteration and we did not investigate how performance varies as the number...

Hi @Astromis , If you use `K = gk.fit_transform(all_graphs)` to produce the kernel matrix, no error is thrown. Thanks for reporting this bug, we will look into it and get...

Hi @JohnLyu2 , The Weisfeiler-Lehman framework is originally designed for undirected graphs. Indeed, it can be generalized to directed graphs, but the implementation in GraKeL at the moment only supports...

Hi @caspervanengelenburg , None of the kernels that are currently implemented in GraKeL support both discrete node labels and continuous node attributes. One workaround would be to initialize the Weisfeiler-Lehman...