can this model work for graphs without lables?

Question

can this model work for graphs without lables?

marasilence opened this issue 6 years ago · 4 comments

Answer 1 · 2019-03-11T12:23:50.000Z

You can use structural properties of nodes (log binned degree, clustering coefficient etc.).

On Mon, 11 Mar 2019 at 12:22, marasilence ***@***.***> wrote: — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#2>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AQk2F2Af1aaN1jlMEVLc_jM70M5w4ov1ks5vVkqUgaJpZM4boeSh> .

Answer 2 · 2019-03-11T12:29:24.000Z

Thanks For your work and your help. How about graphs without node features and labels？I have just adjacency matrix ,can I set all node features as 1?

Answer 3 · 2019-03-11T12:50:43.000Z

No. You can calculate the above mentioned node properties based on the adjacency matrix.

…

On Mon, 11 Mar 2019 at 12:29, marasilence ***@***.***> wrote: Thanks For your work and your help. How about graphs without node features and labels？I have just adjacency matrix ,can I set all node features as 1? — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#2 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AQk2F7TKgwofoblMymB8DT-ZWnhgSk21ks5vVkwkgaJpZM4boeSh> .

Answer 4 · 2019-03-11T13:40:01.000Z

Thanks! @benedekrozemberczki