PLEASE JOIN THIS COMPETITION BEFORE 2021-05-15
Problem Description
During the pandemic, many scientific researchers have devoted themselves to the pathology, transmission, policy, control methods, and other aspects of the epidemic. In addition to biomedical researchers, there are also many scientific researchers from other disciplines who use their related work to analyze and model. and solve the problems caused by the pandemic. It has spawned many interdisciplinary collaborations, cross-domain projects, and academic achievements. 

In scholarly network analysis, there are many issues worthy of our attention. Structurally, the network model is divided into the regular network, random network, small-world network, and a scale-free network. We generally think of it as a scale-free network in the scholar network. In the face of the cooperative relationship between scholars, we often use the clustering coefficient to measure it. By calculating the degree of interconnection between the neighbor nodes of a point, we can know the degree of mutual understanding between scholars. We can use this indicator during the epidemic to know how close the cooperation between scholars is. Related to this is the sparsity of the network, and the cooperation networks in different fields have different sparsity.

Next, we can further analyze the network's topology through different motifs. Some cooperation models are radial, which means that a strong scholar leads some lesser scholars, and some cooperation models are chained, representing scholars. They do not know each other, but they get what they need. There is also a cooperation model that is two radially connected, relying on two influential scholars to cooperate to combine the two big teams. These scholars who have met and cooperated with two initially unknown scholars are identified as critical scholars, and these scholars play an essential role in scientific research.

We can sometimes think that the scholar cooperation network is a small-world network. Such a network often has a smaller average distance and a more significant clustering coefficient. These indicators are all used to measure a community, but How much influence does a point have on the clustering and connectivity of this community? Currently, only centrality indicators can be measured,

We can use betweenness centrality (in the shortest paths of all pairs of nodes in the network, the shortest paths passing through a node, the more influential the node is), closeness centrality (the average distance a node has from other nodes in the network, the more is smaller, the greater the closeness of the node is), the eigenvector centerline (the importance of a node depends on both the number of its neighbors (that is, the degree of the node) and the importance of each neighbor), degree centrality (the more neighbors a node has, the more important it is), semi-local centrality (count the number of second-order neighbors). However, this indicator ignores the attributes of scholars themselves. Therefore, it is far from enough to identify a critical scholar. Therefore, we take the opportunity of the big assignment to discuss the classification of this critical scholar with you.

The data we give contains:

1. A scholar's institution, country, and discipline, from which we can know an essential attribute of a scholar. 
2. When two scholars come from the same institution and are in the same discipline, the cooperation situation is likely to be intra-group cooperation.
3. When two scholars come from different institutions but are still in the same discipline, the cooperation situation is likely to be the cooperation of disciplines.
4. If two scholars come from different countries and disciplines, then the two scholars are engaged in some interdisciplinary, international cooperation, which is likely to be a specific topic that requires joint exploration by multiple countries.

We divide these scholars into four categories:

1. the heart of the network
2. network switch
3. network router
4. network edge node

please design an indicator that can divide the scholars in the network.
Attention
Before submitting your predictions, please update your name with "GroupNumber_StudentName"  before submitting your predictions. You can update your name in the "Team" tab.

For fairness, we set a few rules for you to obey --- violation against the rules will lead to score 
deduction:
1. Please do not copy someone else's code. We will run plagiarism check after 
submission.
2. Please do not download the dataset somewhere else to train your model. We have 
shuffled the dataset and will reproduce your experimental results using the dataset. A 
violation would be considered if there is a big gap between your reported results and our 
reproduced results.
3. Please do not use the pre-trained model. Everything should be built from scratch.
Acknowledgements
Data used in this project is provided by
[Acemap](https://www.acemap.info/)
group.