-
#### Issue Description
Please describe our issue, along with:
- expected behavior
I have a graph containing 3M nodes, 3M edges to be trained to get vectors. And everyday there will be a few new n…
-
When we use the "deepwalk" for the base-embedding, we meet a error, as follows:
AttributeError: Can't pickle local object 'DeepWalk_Original.generate_walks..rnd_walk_workers'
, where the setting par…
-
Traceback (most recent call last):
File "./deepwalk", line 11, in
load_entry_point('deepwalk==1.0.3', 'console_scripts', 'deepwalk')()
File "/usr/local/python36/lib/python3.6/site-packages…
-
Hello,sir
When I run you code I meet some questions , can you tell me how to solve it ?
When I run main.py .My question is as follow:
/home/zhen/HERec-master/venv/bin/python /home/zhen/deep/deepwa…
-
When I set --max-memory-data-size 0, it throws following errors:
Number of nodes: 6301
Number of walks: 63010
Data size (walks*length): 2520400
Data size 2520400 is larger than limit (max-memory-d…
-
Background
=====
- Sense Embeddings: https://arxiv.org/pdf/1805.04032.pdf
- Our sense embedding approach: http://aclweb.org/anthology/W16-1620
Data
====
1. A Distributional Thesaurus …
-
想请教一下，在我的数据集上，DeepWalk的效果远好于Line(2nd order)。DeepWalk离线mrr可以达到0.7+, Line只有0.2+，二者都是无监督Loss。想请教下，这种情况是什么原因呢？我的graph是item同构图，node百万，连边亿级。谢谢。
xuetf updated
5 years ago
-
Hello,
I'm using windows.
I am trying to run Deepwalk on Pycharm with the examples provided. When I test Karate.adjlist, it works perfectly, but when I try to run it with p2p-Gnutella08.edgelist or…
-
why i put acm.mat in deepwalk,it's only 40901 nodes?
-
isn't it wrong to simply assign model.context_embeds with update_nodes+no_update_nodes, where no_update_nodes = tf.stop_gradient(...), for which you meant to stop the gradient for the already trained …