1. 03 Aug, 2023 8 commits
  2. 02 Aug, 2023 1 commit
  3. 01 Aug, 2023 1 commit
  4. 31 Jul, 2023 1 commit
  5. 27 Jul, 2023 6 commits
  6. 14 Jul, 2023 1 commit
  7. 13 Jun, 2023 1 commit
  8. 12 Jun, 2023 1 commit
  9. 09 Jun, 2023 1 commit
  10. 08 Jun, 2023 1 commit
  11. 07 Jun, 2023 2 commits
  12. 10 May, 2023 1 commit
  13. 20 Apr, 2023 1 commit
  14. 10 Apr, 2023 1 commit
  15. 29 Mar, 2023 1 commit
  16. 22 Mar, 2023 1 commit
  17. 15 Mar, 2023 1 commit
  18. 19 Feb, 2023 2 commits
  19. 01 Feb, 2023 1 commit
  20. 12 Jan, 2023 1 commit
  21. 06 Jan, 2023 2 commits
  22. 05 Jan, 2023 1 commit
  23. 05 Dec, 2022 1 commit
    • Dylan's avatar
      GCN example correction (#4969) (#4976) · b84de903
      Dylan authored
      Correction like mentioned in #4969 
      
      I noticed that there is a normalisation step on line 97 while the normalised values are not used downstream. Even if this was meant to show the normalisation step, it would not be calculating the normalisation step described in the CGN paper. The paper considers both in and out degrees while the normalisation in the code only describes normalisation using the in degrees.
      In the end, the normalised values are assigned to g.ndata["norm"] but these values are not used afterwards.
      
      Having a normalisation step here is also unnecessary since the GraphConv layer that is used already takes care of the normalisation. https://docs.dgl.ai/en/0.9.x/_modules/dgl/nn/pytorch/conv/graphconv.html#GraphConv
      
      It confused me for a second thinking that I had to do the normalisation myself but this is already handled by the GraphConf.
      b84de903
  24. 01 Dec, 2022 1 commit
  25. 25 Nov, 2022 1 commit