Project: Fairness-aware Community Detection Method
Description
In real-world networks, nodes are organized into communities and the community size follows power-law distribution. In simple words, there are a few communities of bigger size and many communities of small size. Several methods have been proposed to identify communities using structural properties of the network. These methods can be categorized as (i) label propagation based methods, (ii) Modularity optimization method, (iii) greedy methods, (iv) deep learning based community detection methods.
In this project, we will compare different types of community detection methods from a fairness perspective. We will highlight what kind of approaches are more fair than others. We will further discuss the fairness perspective of different evaluation methods for community detection. Next, given the time, we would like to propose fairness-aware community detection methods.
Fortunato, Santo, and Darko Hric. "Community detection in networks: A user guide." Physics reports 659 (2016): 1-44.
2. Chakraborty, Tanmoy, Ayushi Dalmia, Animesh Mukherjee, and Niloy Ganguly. "Metrics for community analysis: A survey." ACM Computing Surveys (CSUR) 50, no. 4 (2017): 1-37.
Details
- Supervisor
-
George Fletcher
- Secondary supervisor
-
Akrati Saxena
- Interested?
- Get in contact