Issue with Citeseer DataSet Shape

Question

Issue with Citeseer DataSet Shape

samiracs87 opened this issue 4 years ago · comments

Hi there,
There is a discrepancy between the dimensions of data matrices for Citeseer: adjacency matrix is (3327, 3327), while features and labels have 3312 rows which is the number of nodes.
Based on the data source at http://www.cs.umd.edu/~sen/lbc-proj/LBC.html there must be 3312 nodes. Why adjacency matrix has more row/columns than Graph node size in this repo?

Thanks!

Fatima · Answer 1 · Wed Jul 01 2020 18:56:51 GMT+0800 (China Standard Time)

Hi there,
There is a discrepancy between the dimensions of data matrices for Citeseer: adjacency matrix is (3327, 3327), while features and labels have 3312 rows which is the number of nodes.
Based on the data source at http://www.cs.umd.edu/~sen/lbc-proj/LBC.html there must be 3312 nodes. Why adjacency matrix has more row/columns than Graph node size in this repo?

Thanks!

Hi there,

I got the same issue, have you any response for it?
Would be great if you share it.

Cheers

Looomo · Answer 2 · Sun Jul 26 2020 17:36:56 GMT+0800 (China Standard Time)

Same problem . Please let me know if anyone solved this .

samiracs87 · Answer 3 · Mon Jul 27 2020 01:36:49 GMT+0800 (China Standard Time)

Sorry for late reply - I did not get any response and I ended up using the data set from other sources which matches the description.