search

benedekrozemberczki / SimGNN

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).
GNU General Public License v3.0
759 stars 147 forks source link

About dataset #27

Closed Wayne-Bai closed 4 years ago

Wayne-Bai commented 4 years ago

Hi, I have noticed that there are 11000 data in your example, but there are only 100 data in 'data'. How could I get the rest of them?

benedekrozemberczki commented 4 years ago

Generate synthetic data.

On Thu, 4 Jun 2020 at 17:57, Wayne-Bai notifications@github.com wrote:

Hi, I have noticed that there are 11000 data in your example, but there are only 100 data in 'data'. How could I get the rest of them?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/benedekrozemberczki/SimGNN/issues/27, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEETMF2MD4G6MWNOX6EWOFLRU7N7NANCNFSM4NS3IA2Q .

BBBBchan commented 4 years ago

Hi, I have the same question. Well, I can easily generate two graphs as your format, but how could I calculate GED between them?

benedekrozemberczki commented 4 years ago

You can make the editions yourself by changing a base graph.

On Fri, 5 Jun 2020 at 17:56, BB CHAN notifications@github.com wrote:

Hi, I have the same question. Well, I can easily generate two graphs as your format, but how could I calculate GED between them?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/benedekrozemberczki/SimGNN/issues/27#issuecomment-639668431, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEETMFZ42H5Q57W6QOSCYNLRVEWVLANCNFSM4NS3IA2Q .

BBBBchan commented 4 years ago

I consider that it cannot be guaranteed to be optimal alignments.