Research Dublin
Dept. of Computer Science Rutgers
A scalable Approach to Size- independent Network Similarity Michele Berlingerio Tina Eliassi-‐Rad
Danai Koutra Christos Faloutsos
WIN, September 28th-‐29th 2012, NYU Stern School of Business
Why network similarity? (1)
2 x-‐fer
learning
1 Graph
Database: clustering
Danai Koutra (CMU) -‐
[email protected] 2
Why network similarity? (2) 3 Anomaly detec:on:
different models?
4 Discon:nuity Detec:on
Day 1 Day 2 Day 3 Day 4 Day 5 Danai Koutra (CMU) -‐
[email protected] 3
RoadMap • Problem Defini:on • NetSimile • Experiments – Applica