Welcome to Probabilistic Network Analysis
Description: Social networks, biological networks, sensor networks, the WWW, ... all are examples of networks that provide increasingly rich sources of data, and that become an increasingly important subject of study. The common underlying structure, and the similarity of analysis tasks in very different domains concerned with networks has given rise to the emergent discipline of network science. An important element of network science consists of Machine Learning on graph data for network structure analysis and predictive modeling. In this course core Machine Learning techniques for network data are presented.
The focus lies on techniques that build on probabilistic network models, and that apply statistical learning principles (however, some classical non-probabilistic approaches will also be discussed).
The scope of the course is (approximately) described by the following topics:
- Random graph models; power laws;
- Graph clustering/community detection
- Node classification and link prediction
- Random walk models: pagerank, hitting times, commute times
- Multi-relational graphs and statistical relational learning
Prerequisites: Basic knowledge of probability theory and statistical inference. Ability to install and use a network analysis toolbox in the form of R or Matlab libraries.
Learning objectives: To understand basic principles and techniques of probabilistic network analysis. Ability to read current research papers applying probabilistic analysis techniques.
Organizer and lecturer: Associate Professor Manfred Jaeger, AAU, email: firstname.lastname@example.org
Time: 29, 30 May and 1 June 2017
Place: Selma Lagerløfs Vej 300, room 02.90
Zip code: 9220
Number of seats: 25
Deadline: 15 May 2017
Important information concerning PhD courses We have over some time experienced problems with no-show for both project and general courses. It has now reached a point where we are forced to take action. Therefore, the Doctoral School has decided to introduce a no-show fee of DKK 5,000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately three months before start. This can hopefully also provide new students a chance to register for courses during the year. We look forward to your registrations.
- Teacher: Manfred Jaeger