deepwalk-master
所属分类：人工智能/神经网络/深度学习
开发工具：Python
文件大小：1286KB
下载次数：1
上传日期：2018-03-03 19:58:37
上 传 者：
zjg
说明： skipgram的deepwalk算法，复杂网络节点表征学习文中有部分地方还是有很大的改进空间的，比如随机游走过程，本文提出的更像是随机地进行深搜，后来的很多文章，例如LINE、Node2vec都有在这方面有进行改进。还有一点就是LINE里面提到的，Deepwalk中没有提出一个明确的目标函数（这是不是机器学习专家的职业病，非得把问题转化为最优化问题…）
(Deepwalk skipgram algorithm, the complex network node in the characterization of learning is in part or there is much room for improvement, such as a random walk, this is more like a random deep search, many articles later, such as LINE and Node2vec are in this area has improved. Another point is that in LINE, Deepwalk didn't put forward a clear objective function. It's not a machine learning expert's occupational disease. It has to transform the problem into an optimization problem.)
文件列表:
.travis.yml (308, 2016-03-26)
AUTHORS.rst (148, 2016-03-26)
CONTRIBUTING.rst (3161, 2016-03-26)
HISTORY.rst (255, 2016-03-26)
LICENSE (35399, 2016-03-26)
MANIFEST.in (243, 2016-03-26)
Makefile (1273, 2016-03-26)
deepwalk (0, 2016-09-29)
deepwalk\__init__.py (117, 2016-03-26)
deepwalk\__main__.py (5951, 2016-03-26)
deepwalk\graph.py (7292, 2016-03-26)
deepwalk\skipgram.py (2157, 2016-03-26)
deepwalk\walks.py (2866, 2016-03-26)
deepwalk.bib (738, 2016-03-26)
docs (0, 2016-09-29)
docs\Makefile (6777, 2016-03-26)
docs\authors.rst (27, 2016-03-26)
docs\conf.py (8405, 2016-03-26)
docs\contributing.rst (32, 2016-03-26)
docs\history.rst (27, 2016-03-26)
docs\index.rst (504, 2016-03-26)
docs\installation.rst (193, 2016-03-26)
docs\make.bat (6466, 2016-03-26)
docs\usage.rst (73, 2016-03-26)
example_graphs (0, 2016-09-29)
example_graphs\blogcatalog.mat (1255783, 2016-03-26)
example_graphs\karate.adjlist (500, 2016-03-26)
example_graphs\p2p-Gnutella08.edgelist (215172, 2016-03-26)
example_graphs\scoring.py (3297, 2016-03-26)
requirements.txt (113, 2016-03-26)
setup.cfg (21, 2016-03-26)
setup.py (1462, 2016-03-26)
tests (0, 2016-09-29)
tests\__init__.py (23, 2016-03-26)
tests\test_deepwalk.py (387, 2016-03-26)
... ...
===============================
DeepWalk
===============================
DeepWalk uses short random walks to learn representations for vertices in graphs.
Usage
-----
**Example Usage**
``$deepwalk --input example_graphs/karate.adjlist --output karate.embeddings``
**--input**: *input_filename*
1. ``--format adjlist`` for an adjacency list, e.g::
1 2 3 4 5 6 7 8 9 11 12 13 14 18 20 22 32
2 1 3 4 8 14 18 20 22 31
3 1 2 4 8 9 10 14 28 29 33
...
2. ``--format edgelist`` for an edge list, e.g::
1 2
1 3
1 4
...
3. ``--format mat`` for a Matlab MAT file containing an adjacency matrix
(note, you must also specify the variable name of the adjacency matrix ``--matfile-variable-name``)
**--output**: *output_filename*
The output representations in skipgram format - first line is header, all other lines are node-id and *d* dimensional representation::
34 ***
1 0.016579 -0.033659 0.342167 -0.0469*** ...
2 -0.007003 0.265891 -0.351422 0.043923 ...
...
**Full Command List**
The full list of command line options is available with ``$deepwalk --help``
Requirements
------------
* numpy
* scipy
(may have to be independently installed)
Installation
------------
#. cd deepwalk
#. pip install -r requirements.txt
#. python setup.py install
Citing
------
If you find DeepWalk useful in your research, we ask that you cite the following paper::
@inproceedings{Perozzi:2014:DOL:2623330.2623732,
author = {Perozzi, Bryan and Al-Rfou, Rami and Skiena, Steven},
title = {DeepWalk: Online Learning of Social Representations},
booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
series = {KDD '14},
year = {2014},
isbn = {978-1-4503-2956-9},
location = {New York, New York, USA},
pages = {701--710},
numpages = {10},
url = {http://doi.acm.org/10.1145/2623330.2623732},
doi = {10.1145/2623330.2623732},
acmid = {2623732},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {deep learning, latent representations, learning with partial labels, network classification, online learning, social networks},
}
Misc
----
DeepWalk - Online learning of social representations.
* Free software: GPLv3 license
* Documentation: http://deepwalk.readthedocs.org.
.. image:: https://badge.fury.io/py/deepwalk.png
:target: http://badge.fury.io/py/deepwalk
.. image:: https://travis-ci.org/phanein/deepwalk.png?branch=master
:target: https://travis-ci.org/phanein/deepwalk
.. image:: https://pypip.in/d/deepwalk/badge.png
:target: https://pypi.python.org/pypi/deepwalk
近期下载者：
相关文件：
收藏者：