alibaba / alibaba/euler

Node2vec模型的几个疑问?

Open
#5 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
2.9k
Forks
553
PR merge metrics
No merged PRs in 30d

Description

首先感谢开源这么好的框架!
在[run_loop.py](https://github.com/alibaba/euler/blob/master/tf_euler/python/run_loop.py)第200行,我注意到`Node2Vec`模型后面几个参数(如`walk_len`)都是不支持自定义的。
另外,在模型编写一节,
> 将DeepWalk套入到上面的范式中,其实现可以分为以下三步:
> 1. 从顶点进行随机游走生成源点正例对,并采样出负例;
> 2. 将源点、正例和负例embedding到向量;
> 3. 从源点、正例和负例的embedding向量计算出交叉熵loss和mrr。

因此,对于`Node2vec`我有下面这几个疑问,感谢您的解答。
Q1. 后续`walk_len`等这些参数会支持自定义吗?
Q2. 是不是`walk_len`和`num_negs`分别表示对于某一个源点的正例和负例的数量?
   `walk_len`不适合设置过大的值吗(如`40`)?
   `walk_len`是不是和`word2vec`中的`window_size`参数的含义是相似的?
Q3. `num_negs, walk_len, left_win_size, right_win_size`的建议取值范围是怎样的?

Contributor guide

No contributing guide indexed for this repository

Research direction

Read python/run_loop.py around line 200 and the model-writing section cited in the issue. Trace the Node2Vec arguments and compare them with the documented DeepWalk and Word2Vec concepts. Done means the parameter configurability, meanings, and suggested ranges are answered or documented clearly.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.