# DeepWalk Online Learning of Social Representations

## April 18, 2015

DeepWalk: Online Learning of Social Representations》是一篇我个人非常喜欢的论文，不仅提出了一个想法，更展示了这个想法的可行性和可能空间。提出的想法是利用网络结构信息将用户表示为低维实值向量，学出来的表示是最重要的，因为有了表示就可以用来加在许多其他任务上。

• 观察是：

If the degree distribution of a connected graph follows a power law (is scale-free), we observe that the frequency which vertices appear in the short random walks will also follow a power-law distribution

• 迁移是：源于这个 frequency，作者想到了 NLP 中的 word frequency。word frequency 在 NLP 中有一个基本的假设是，在同一个文本语料中是同分布的。由此带来了 frequency -> distribution 的一种关联，作者将这种关联“迁移”到了他的模型中，进而将 NLP 中的 distributed word representation 思想用在了 social network 中的节点表示上。

A core contribution of our work is the idea that techniques which have been used to model natural language (where the symbol frequency follows a power law distribution (or Zipf ’s law)) can be re-purposed to model community structure in networks.

P.S.:作者这个实验室我发过几次邮件，非常热情细致，回复得特别仔细，好实验室啊。

### Highway Networks and Deep Residual Networks

Recently, a breakthrough news spread over social networks. In this post, I will explain this ResNet as a special case of Highway Networks, which has been proposed before. Both of the work is amazing and thought-provoking. Continue reading

#### NIPS 2015 Deep Learning Symposium Part II

Published on January 09, 2016

#### NIPS 2015 Deep Learning Symposium Part I

Published on December 11, 2015