Community Discovery for Complex Networks

Given: a network, especially a large one, directed or not, weighted or not.

Desired: a sensible decomposition of the graph into sub-graphs, wherein the nodes in each sub-graph have more to do with each other than with outsiders, i.e., form communities.

This is also called “module detection“.

Ref from here

Continue reading


Papers on TDA

Unread (new)

Read & Categorized


  • H. Edelsbrunner and J. Harer, Computational Topology. An Introduction. (Amer. Math. Soc., 2010).
  • H. Edelsbrunner, D. Letscher, and A. Zomorodian, Topological persistence and simplificationDiscrete Comput. Geom. 28, 511 (2002)

Material science

Kernel method

Time-series + Dynamic system





My recent work in Recommendation System

Need time to write up.


Yelp is an online urban guide that helps people find recommended destinations based on the informed opinions and reviews of a community.

Goal: the high level goal of this project is to apply existing built-in PredictionIO engines to a new domain and new dataset.

For this project you will build a restaurant recommendation engine (see Yelp) using built-in Item Recommendation engine and the Yelp dataset.


Yelp dataset via Kaggle –

Demo link: