## Abstract

Recently there has been much interest in graph-based learning, with applications in collaborative filtering for recommender networks, link prediction for social networks, fraud detection and graph search techniques. Many of these applications use random walks on graphs in order to exploit structural information from the underlying graphs. I will discuss some basics of random walks on graphs and various proximity measures arising out of random walks. I will briefly outline a few well-known random walk based approaches for collaborative filtering, link prediction in social networks and personalized pagerank. This is not a talk about my research, but a survey of a research area of interest to the Machine Learning community.

## Bio

## Venue, Date, and Time

Venue: NSH 1507

Date: Monday, October 1

Time: 12:00 noon