graphwave

graphwave copied to clipboard

when there are millions of nodes,compute the full eigendecomposition of a large matrix will get "MemoryError"

3

when there are millions of nodes,compute the full eigendecomposition of a large matrix will get "MemoryError" , so this method can't be used to big community.

chenwgen

hi, sorrry to bother. I recently want to replicate the experiment of table 1 in paper。the paper says the varied graph results comes from doing experiment on a circle with...

maxmit233

hello, can you provide enron email network for me? i get it from http://snap.stanford.edu/data/email-Enron.html but without role label. thanks

ghost

different nodes' embeddings are quite similar in their absolute value in each dimension. Do you perform some column normalization for the downstream task, e.g. the node structure role classification? In...

ShengdingHu

is this algorithm memory efficient?

1

I did construct a graph with 39000 nodes and 1 million edges,not util the algorithm computation finished,the memory used already coming up to about 124GB,is this normal? Is there other...

fanlinbo

I want to use GraphWave to process a weighted network, what are the requirements for weights of edges? such as range or sum

Tirami-su

Several bugs with 'Using GraphWave' iPython notebook

1

Thanks for putting together the tutorial in the iPython notebook! While trying to use it, I came across the following bugs and suggested fixes: 1. `from graphwave.shapes import build_graph` should...

motiwari

Is the order of the vectors sorted by the number of the nodes from small to large?

1

Fungker

calculate similarity between nodes

3

I am trying to calculate similarity coefficients between nodes based on node embedding vectors obtained from graphwave algorithm. However, the calculated distance between node embedding vectors is very small, e.g....

mousewu

I think this would really help make it easier to use! The package could use a `setup.py` :)

motiwari