zealscott / hakg Goto Github PK

您好，可以提供下处理过的yelp2018数据集嘛，代码中只提供了处理过的的alibaba-ifashion数据集。

你好，请问能提供其他几个数据集吗？

你好，我注意到你在庞加莱圆盘模型上计算实体embedding时，论文中公式是:

这里说明embedding是在圆盘上面的，而你代码上面:

我直观上理解为: 每次计算时都将嵌入先投影到圆盘模型上面，然后进行Mobius addition，再投回切空间进行聚合，这样的话其实实体embedding结果不应该还是在切空间吗?这样和论文里的公式是不是有点不符合

我使用的是Dataparallel，一直出现这样的问题，请问我是哪里出错了

你好，关于hakg的论文看完了。
为了直接运行代码，
我想获得Yelp 2018 raw dataset，但因为我是外国人，所以没能加入qq网站，无法下载review数据。 如果不失礼的话，希望通过谷歌驱动链接共享数据。

谢谢。

multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "D:\ProgramData\Anaconda3\envs\hakg\lib\multiprocessing\pool.py", line 125, in worker
result = (True, func(*args, **kwds))
File "D:\ProgramData\Anaconda3\envs\hakg\lib\multiprocessing\pool.py", line 48, in mapstar
return list(map(*args))
File "D:\download\HAKG-main\HAKG-main\utils\evaluate.py", line 92, in test_one_user
user_pos_test = test_user_set[u]
NameError: name 'test_user_set' is not defined
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "main.py", line 123, in
ret = test(model, user_dict, n_params)
File "D:\download\HAKG-main\HAKG-main\utils\evaluate.py", line 168, in test
batch_result = pool.map(test_one_user, user_batch_rating_uid)
File "D:\ProgramData\Anaconda3\envs\hakg\lib\multiprocessing\pool.py", line 364, in map
return self._map_async(func, iterable, mapstar, chunksize).get()
File "D:\ProgramData\Anaconda3\envs\hakg\lib\multiprocessing\pool.py", line 771, in get
raise self._value
NameError: name 'test_user_set' is not defined

Why is the model code inconsistent with your paper description?

What is the license policy for this project?
Please indicate in the README.

when I run the code,I find that I have to change
graph_tensor = torch.tensor(list(graph.edges)) to
graph_tensor = torch.tensor(list(graph.edges(keys=True))) in HAKG.py,line224.
Otherwise the keys will not be shown in graph.edges().Maybe it's caused by the version of networkx.Hope this can help those who have the same problem.