Resume
 Publications
 Courses
 Teaching
 Tools
 Quick Links
Leman Akoglu
PhD student
 
Computer Science Department
Carnegie Mellon University
Pittsburgh, PA 15213
Pittsburgh weather
 
Office: Gates Hall Center 9021
Phone: (412) 268-5636
 
email
 
 
 
I am a PhD student in the Computer Science Department at Carnegie Mellon University since Fall 2007. My primary research interests are in data mining and databases. I also have interest in machine learning applications to data mining. Currently I am working with my advisor Christos Faloutsos on social network analysis and large graph mining. In particular, we try to find interesting patterns/anomalies in weighted, time-evolving, large real-world graphs using scalable algorithms and tools. Here is my resume in [pdf].

Publications
  • Nan Du, Christos Faloutsos, Bai Wang, Leman Akoglu. Large Human Communication Networks: Patterns and a Utility-Driven Generator. ACM SIGKDD, Paris, France, June 2009. [pdf]
  • Leman Akoglu, Mary McGlohon, Christos Faloutsos. RTM : Laws and a Recursive Generator for Weighted Time-Evolving Graphs. ICDM IEEE International Conference on Data Mining, Pisa, Italy, Dec. 2008. [pdf] [ppt]
  • Mary McGlohon, Leman Akoglu, Christos Faloutsos. Weighted Graphs and Disconnected Components: Patterns and a Generator. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, NV, Aug. 2008. [pdf] [ppt]

Technical Reports

  • L. Akoglu, M. McGlohon, C. Faloutsos. RTM : Laws and a Recursive Generator for Weighted Time-Evolving Graphs. Carnegie Mellon University Technical Report: CMU-CS-08-161. [pdf]



Courses

  • *Advanced Computer Architecture , Spring 2009. [ Project report / Poster ]
  • *Type Systems for Programming Languages, Fall 2008.
  • Probabilistic Graphical Models, Fall 2008. [ Project report / Poster ]
  • *Graduate Algorithms, Spring 2008.
  • Multimedia Databases and Data Mining, Spring 2008. [ Project report / Poster ]
  • *Machine Learning, Fall 2007. [ Project report / Poster ]
  • Spectral Graph Theory and Scientific Computing, Fall 2007.


    • Teaching

     15-415 Database Applications Fall 2009 , Instructor: Christos Faloutsos


    Tools

    If you are interested in weighted graph mining or want to repeat experiments from our KDD'08 paper (patterns and disconnected components) for other datasets you may have, you can use the following package:     [KDD08_tbox.tar.gz]

    Another software package for spotting anomalous nodes (near-cliques/stars, heavy vicinities, almost isolated stars, etc.) in weighted graphs is to come soon... . Please contact me for comments and/or questions.


    Quick Links