Vagelis Papalexakis, graduate student

Telecommunications Division
Department of Electronic & Computer Engineering
Technical University of Crete
Office 145.A11
Tel.: +30-28210-37324

CV: English
E-mail: vag_papalexyahoo.gr , vagelistelecom.tuc.gr

Hello! My name is Vagelis Papalexakis. I recently received the ECE Diploma degree from the Technical University of Crete.
I am now a post-graduate student @ the ECE department of TUC, under the supervision of professor Nikos Sidiropoulos.
This fall, I will be joining the Computer Science Department of Carnegie Mellon University as a PhD student.
Click here to access my new webpage at Carnegie Mellon.


Research Interests

My research is focused on the application of Signal Processing algorithms, Multiway Analysis, and Optimization methods to Data Mining and Co-clustering.

Conference & Workshop Publications


Copyright © as noted on each article. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new
collective works for resale or redistribution must be obtained from the copyright owner. By choosing to view one of these articles, you agree to all provisions of the copyright laws protecting it.

(3) Evangelos E. Papalexakis, Nicholaos D. Sidiropoulos, Co-clustering as multilinear decomposition with sparse latent
factors, IEEE ICASSP 2011, Prague, Czech Republic Paper Poster

(2) Evangelos E. Papalexakis, Nicholaos D. Sidiropoulos, Minos Garofalakis, Reviewer Profiling Using Sparse Matrix
Regression, IEEE OEDM 2010 Workshop, held in conjuction with ICDM 2010, Sydney, Australia Paper Talk Slides

(1) Nicholaos D. Sidiropoulos, Evangelos E. Papalexakis, Three-way Co-clustering, SIAM workshop on Tensor Decompositions
and Applications (TDA 2010), Monopoli, Bari, Italy, 13-17 September 2010



Theses & Projects


Diploma Thesis

I completed my diploma thesis under the supervision of professor Nikos Sidiropoulos, with title "Reviewer Profiling Using Factor Analysis".
You can download the full text and the presentation slides, both in .pdf format. I provide here a cvx-based implementation of the algorithms
used as basis for my thesis. I also provide a demo of GoogleScholarMiner as presented on my thesis.


Non-Negative Matrix Factorization:source code
PARAFAC w/ Non-negativity Constraints: source code
GoogleScholarMiner Demo: source code

You need to have Matlab (and cvx, in the case of NMF & PARAFAC) installed, in order to execute the above files.
In the case of GoogleScholarMiner, you also need to have Java installed in your computer.