CS 6604: Fall 2015
Data Mining Large Networks
and Time-Series

Description

Can we guess if a user is sick from her tweet? How do opinions get formed in online forums? Which people should we immunize, to prevent an epidemic as fast as possible? How to quickly zoom out of a graph? Graphs---also known as networks---are powerful tools for modelling processes and situations of interest in real-life like social-systems, cyber-security, epidemiology and biology. They are ubiquitous, from online social networks, gene-regulatory networks, to router graphs.

This course will cover recent research on the analysis of large networks (both theoretical and empirical), algorithms behind network problems, and their practical applications in various diverse settings. Topics include diffusion and virus propagation in networks, community detection, anomaly and outbreak detection, time-sequence segmentation and connections with work in public health, social sciences and cyber security.

Course Information

Textbooks and Resources

There is NO required textbook. Recommended reading: See other resources (pointers to datasets, code etc.) here.

Announcements

Schedule (tentative)

For lecture slides and readings, go here.
  1. Introduction
  2. Graphs: Definitions and ER model
  3. Small worlds and Power Laws
  4. Dynamics of Networks and Models
  5. Centrality Measures
  6. Epidemics: Models and Theory
  7. Viral Marketing and Outbreak Detection
  8. Immunization
  9. Finding sources
  10. Link Prediction
  11. Competing viruses and time-varying networks
  12. Spectral analysis and graph clustering
  13. Anomaly Detection
  14. Graph analysis on Hadoop
  15. Time-Series Mining
  16. Time-Series Forecasting
  17. Meme tracking

Acknowledgements

Amazon's AWS in Education grant program for generously providing support for Amazon Web Services.