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.)