diningphil/gnn-comparison

Issues

• Results don't match - am I running something in the wrong way?

  #53 opened 3 months ago by levyofek
  1

• GraphSage doesn't learn.

  #50 opened 4 months ago by ssantos97
  12

• Can't find device = cuda in config files

  #43 opened 10 months ago by YoavLotem
  1

• error message

  #29 opened a year ago by cxw-droid
  1

• PyTorch -- multiple threads for each process

  #17 opened 3 years ago by ersisimou
  2

• additional features

  #16 opened 4 years ago by pursueorigin
  1

• Different best config in each k_fold

  #4 opened 4 years ago by wymli
  6

• Call each other

  #15 opened 4 years ago by rym21
  2

• Using dropout in last layer

  #14 opened 4 years ago by foxtrotmike
  1

• Using DGCNN with new data

  #12 opened 4 years ago by ferdisvea
  1

• The program crashes without "--debug" flag being set when using Cuda.

  #11 opened 4 years ago by MhYao2014
  1

• the dataset for the experiments

  #7 opened 4 years ago by CODE-SUBMIT
  1

• The position of "config_id += 1" in the 84 of evaluation/model_selection/HoldOutSelector.py

  #9 opened 4 years ago by JennyyiqiW
  1

• It takes long time to train DiffPool

  #10 opened 4 years ago by LucasSlovenia
  1

• Multi-process running errors

  #8 opened 4 years ago by JennyyiqiW
  4

• Not a question, the code is running well. Thanks.

  #6 opened 4 years ago by xma24
  0

• DiffPool breaks on ENZYMES?

  #5 opened 4 years ago by urialon
  5

• OUTER_TS is 20.0 FOR M5k(GraphSAGE)

  #3 opened 4 years ago by CODE-SUBMIT
  2

• Is there a mistake in Data Preprocessing?

  #2 opened 4 years ago by JindongGu
  2

• Best configs / splits

  #1 opened 4 years ago by urialon
  3