RotatE: this implementation vs GraphVite #14

Activity

1. Edward-Sun commented on Oct 24, 2019

   

   Edward-Sun

   on Oct 24, 2019

   Collaborator

   More actions

   Hi,
   Thank you for your interest in both projects. The essential differences between this implementation and GraphVite implementation are listed as following:

   1. GraphVite uses ASGD rather than mini-batch SGD，the gradient information in GraphVite is relatively noisier.
   2. Considering the numeric stability in ASGD, GraphVite reduces the number of negative samples from 256 to 64.
   3. For a fair comparison with other large-scale KGE systems, the reported benchmark performance of GraphVite is undertrained. GraphVite can achieve better performance when using a single GPU and train for a longer time.

   👍React with 👍4Reacted by Andrea Rossi, Zawo1995, Diison and 5zongyuan
2. KiddoZhu commented on Oct 25, 2019

   

   KiddoZhu

   on Oct 25, 2019

   Member

   More actions

   @AndRossi All the technical reasons have been pointed out in the author's comment above.

   GraphVite is targeted at speed and scalability so there is slight difference in performance. Actually such gap could be easily covered by some hyperparameter hacking (e.g. double the dimension of embedding or training length), but we keep the original setting to make it a clean system work.

   If you want to use KGE as an off-the-shelf tool, it is recommended to use GraphVite. If you want to develop new SOTA methods for KGE, it is recommended to use this repo.

   👍React with 👍5Reacted by Andrea Rossi, Zawo1995, Ali Sadeghian, sameerspatil and Aoi Ohta