Code for entity classification task
PlusRoss opened this issue · comments
Hi,
Thanks for this amazing work! May I have your code for entity classification task?
I am interested in the implementation of node classification, too.
Sure, I will try to include that asap. Currently stuck with some work.
Hi, I can not reproduce the performance of the proposed model on node classification task, and I'm not sure if the hyper-parameters are set incorrectly.
Can you show the hyper-parameter settings of node classification, including the number of relation basis vectors, dropout rate, l2 penalty and other related detalis?
Traceback (most recent call last):
File "/home/ubantu/anaconda3/lib/python3.7/site-packages/torch_scatter/init.py", line 13, in
library, [osp.dirname(file)]).origin)
File "/home/ubantu/anaconda3/lib/python3.7/site-packages/torch/_ops.py", line 106, in load_library
ctypes.CDLL(path)
File "/home/ubantu/anaconda3/lib/python3.7/ctypes/init.py", line 364, in init
self._handle = _dlopen(self._name, mode)
OSError: libtorch_cpu.so: cannot open shared object file: No such file or directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "run.py", line 1, in
from helper import *
File "/media/ubantu/fb915eb5-f0ce-4b0a-8cc4-4e941d52b4b4/lmh/CompGCN-master(Modified)/helper.py", line 13, in
from torch_scatter import scatter_add
File "/home/ubantu/anaconda3/lib/python3.7/site-packages/torch_scatter/init.py", line 21, in
raise OSError(e)
OSError: libtorch_cpu.so: cannot open shared object file: No such file or directory
Any plan to include the node classification code? Running on a single dataset is fine as well.
An implementation of node classification experiments can be found here:
zhjwy9343/dgl#8