要展现你的leadership ，就要take the initiative 去思考回答困扰整个团队的问题， 不断一起update各自的思考；千万不要等着别人来推动自己，那样就在智力上成了别人的附庸，整个团队也会向paper factory 演化，所有人都会很累的。
对于畏惧数学的同学，我想借用爱因斯坦的话来安慰大家：Before God we are all equally wise and equally foolish. Do not worry about your difficulties in Mathematics. I can assure you mine are still greater. 更进一步，我想说在计算社会科学领域当中所使用到的数学绝大多数是高中数学的水平，有时会涉及到一些社会统计的内容，高深的数学则并非必要。
- 我推荐安装anaconda python 3.x版本，然后使用其中的jupyter notebook来编写代码，这样所有的计算过程都可以记录下来，便于交流和展示。
The spread of true and false news online
We are indebted to Twitter for providing funding and access to the data. We are also grateful to members of the MIT research community for invaluable discussions. The research was approved by the MIT institutional review board. The analysis code is freely available at https://goo.gl/forms/AKIlZujpexhN7fY33. The entire data set is also available, from the same link, upon signing an access agreement stating that (i) you shall only use the data set for the purpose of validating the results of the MIT study and for no other purpose; (ii) you shall not attempt to identify, reidentify, or otherwise deanonymize the data set; and (iii) you shall not further share, distribute, publish, or otherwise disseminate the data set. Those who wish to use the data for any other purposes can contact and make a separate agreement with Twitter.
- Barabási, Albert-László; Albert, Réka. (October 15, 1999). "Emergence of scaling in random networks". Science. 286 (5439): 509–512.
- R. Albert, A.-L. Barabási. Statistical mechanics of complex networks. Reviews of Modern Physics 74, 47-97 (2002) 
- H. Jeong - Z. Néda - A. L. Barabási (2003) Measuring preferential attachment in evolving networks. Europhys. Lett., 61 (4), p. 567 
Poincaré Embeddings for Learning Hierarchical Representations
Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this property. For this purpose, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space – or more precisely into an n-dimensional Poincaré ball. Due to the underlying hyperbolic geometry, this allows us to learn parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. We introduce an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincaré embeddings outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability.
PyTorch implementation of Poincaré Embeddings for Learning Hierarchical Representations https://github.com/facebookresearch/poincare-embeddings
My Teaching Philosophy
Teaching is one process of self-presentation, through which you represent the long-living knowledge of human kind. It really matters what you are thinking about your teaching philosophy. For me, according to my understandings of teaching, I would like to highlight the equality of teaching and learning, the nature of human beings, and being open-minded.
Everyone is equal
Respect Your AudienceA good lesson I learnt from this class come with a question: what should you do when your students did a good job? If not, what will you do? Reflect about the answer. Do you want to reward or punish them? Remember your answer in heart.
I would like to introduce Skinner’s box invented by Frederic Skinner, which contains levers that an animal can press, stimulus lights, electric grid, and food pellet. Following the logic of behaviorism, when the subject correctly performs the behavior, the chamber mechanism delivers food or another reward. Or else, the box delivers a punishment for incorrect or missing responses.
Thus, you may realize that you are treating your students as passive experimental subjects. The beginning point is never to treat your students as experimental rats, and even animals deserve your respects. Students are human beings who have their own feelings, emotions, and values. The first step of teaching should be to learn to respect your audiences, even though they behave passively, or make no progress.
Understanding human nature
Effective teaching is to impose a set of values & beliefs on the student. The most important part should be teaching the students how to learn. The best way of learning should be acting according to the nature of human beings. Everyone had been a curious kid who wanted to explore every part of the world. Just like the cat is curious about the fish (sometime, for eating, while sometimes just for fun), human beings, in the nature, are curious about the part of knowledge they are interested in. The second step of effective teaching should be inspiring your students to fulfill their interests in the learning process.
I was always not surprised about the story of Thomas Suarez, the 12 years old kid who made two iphone Apps by learning python, java, and c. Little Thomas has been fascinated by computers and technology before kindergarten. What the teacher should think is how could we contribute to the audiences’ real interests, rather than beat around the bush complaining why the students have no passion in the boring class.
The world is always changed by new comers. The teacher will finally find his or her understandings about the cutting-edge scientific study are not perfect. The best way is not to constrain the students from challenging the tradition. Being open-minded, sit down, and enjoy the new outline drawn by the young people.