Have you used this code to verify the experiment in the paper? How is the result compared to the paper?

[xuequeen]

Have you used this code to verify the experiment in the paper? How is the result compared to the paper?

[apple2373]

no. i didn't do the reproducing experiment. I recommend author's own implementation if you are looking for verified implementation.

…

On Mon, Apr 9, 2018, 05:09 xuequeen ***@***.***> wrote: Have you used this code to verify the experiment in the paper? How is the result compared to the paper? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#3>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AH4D4zRYqehcKM5k4iKq6afxAut16Ik-ks5tmyVVgaJpZM4TMMXm> .

[960924]

Have you used this code to verify the experiment in the paper? How is the result compared to the paper?

Have you done the relevant experiment? I used the node representation generated by the author's code, but the classification effect is only about 0.6. I don't know what is wrong.