Questions tagged [stellargraph]
23 questions
1
vote
0 answers
Cant use stellargraph library from google colab
I have been trying to run a certain notebook in google colab with the use of stellargraph library
I am using this command to install stellargraph (required version is 1.2.1)
Note: I changed the python to 3.7.16
%pip install -q…

Saar
- 11
- 2
1
vote
0 answers
TypeError: Cannot iterate over a Tensor with unknown first dimension
Getting the following error when I execute the below code:
TypeError: Cannot iterate over a Tensor with unknown first dimension.
How to solve this? The error is in the line output_gcn = gcn(input_layer)
I tried reshaping the input_layer, but it…

kini.kg
- 11
- 1
1
vote
1 answer
StellarGraph PaddedGraphGenerator - how to provide specific training, validation and test sets
I'm trying to train a basic Graph Neural Network using the StellarGraph library, in particular starting from the example provided in [0].
The example works fine, but now I would like to repeat the same exercize removing the N-Fold Crossvalidation…

hwktmp
- 33
- 1
- 4
1
vote
1 answer
Pycharm backend issue
I see that this is a common issue but I have yet to see a fix for it. I am using the latest pycharm community, and i am running a script from the python console, but any time I try to load matplotlib or stellargraph in particular, I get the…

TSirico
- 35
- 5
1
vote
1 answer
Algorithm design: Find CCs containing specific nodes from a large edge list
Given: Large edge list, with about 90-100 million edges, 2 million nodes. These edges compose a giant graph with thousands of connected components.
I also have a list of nodes of interest. I want to extract the edges of only the CCs containing these…

Jonathan
- 1,876
- 2
- 20
- 56
1
vote
1 answer
Watch-your-step model with StellarGraph is not working on a GPU
I am trying to train a large graph-embedding using WatchYourStep algorithm using StellarGraph.
For some reason, the model is only trained on a CPU and not utilizing the GPUs.
using:
TensorFlow-gpu 2.3.1
having 2 GPUs , cuda 10.1
running inside an…

Dror Hilman
- 6,837
- 9
- 39
- 56
0
votes
0 answers
Keras model predicting different outputs for the same input
I am using stellargraph for learning a GraphSage model. This is my code:
num_samples = [10, 5]
unsupervised_samples = UnsupervisedSampler(G,nodes=G.nodes(),length=10, number_of_walks=5)
# Generate training data for the encoder model
generator =…

Bob
- 23
- 5
0
votes
0 answers
How to pass Stellargraph as an input to Keras model?
I am unable to pass Stellargraph graph as an input to Keras model using Input().
It gives an error:
Failed to find data adapter that can handle input: ,
Is there a way to define input…

Aks
- 3
- 2
0
votes
1 answer
How to add new node attributes to an already created stellargraph graph?
I have a graph
StellarGraph: Undirected multigraph
Nodes: 4, Edges: 10
Node types:
default: [4]
Features: float32 vector, length 2
Edge types: default-default->default
Edge types:
default-default->default: [10]
Weights:…

Aks
- 3
- 2
0
votes
0 answers
What to use a node feature on the hinSAGE algorithm?
I have a graph with this info:
StellarDiGraph: Directed multigraph
Nodes: 1417, Edges: 1988
Node types:
ParagraphA: [429]
Features: float32 vector, length 1417
Edge types: A-contains->D, A-contains->F, A-contains->E
PrecedentB: [332]
Features:…

Red Boraley
- 21
- 2
0
votes
0 answers
GCN steller graph: train_gen = generator.flow(train_subjects.index, train_targets)
I am using GCN from Steller Graph with Cora dataset from CSV files (not default dataset). It gives me an error: raise KeyError(missing_values) at train_gen = generator.flow(train_subjects.index, train_targets).
The error is given below.…

wasif khan
- 27
- 6
0
votes
0 answers
How can I use StellarGraph BiasedRandomWalk function to walk only over nodes with a specific attribute?
I work in the medical field and have a networkx MultiDiGraph G representing Human Phenotype Ontology (HPO) numenclature of symptoms.
For example, 'Macrocephaly at birth' with HPO id HP:0004488 is a clinical symptom and is connected upstream to a…

raphael
- 1
0
votes
1 answer
Incompatible shapes in Stellargraph
I'm trying to implement a small prototype of The GCN Model using the library Stellargraph. I've my StellarGraph graph object ready, I'm trying to solve a multi-class multi-label classification problem. This means I'm trying to predict more than one…

Muhammad Ezzat
- 97
- 6
0
votes
1 answer
Linkprediction using Hinsage/Graphsage in StellarGraph returns NaNs
I am trying to run a link prediction using HinSAGE in the stellargraph python package.
I have a network of people and products, with edges from person to person (KNOWs) and person to products (BOUGHT).
Both people and products got a property vector…

Bjørn Øst Hansen
- 179
- 1
- 2
- 9
0
votes
1 answer
Stellargraph and Node2Vec embedding
I'm trying to do a link prediction with stellargraph, following the documention tutorial.
When I reach this part :
def node2vec_embedding(graph, name):
rw = BiasedRandomWalk(graph)
walks = rw.run(graph.nodes(), n=num_walks,…

Reine Baudache
- 413
- 4
- 16