Latent Structures in Large-scale Networks with Censored Data
Abstract: Recovering latent structures is a key unsupervised learning task in network data with applications spanning across a multitude of disciplines. For example, identifying communities in webpages can lead to faster search, classifying regions of the human brain in communities can be used to predict onset of psychosis, and identifying communities of assets can help investors manage risk by investing in different communities of assets. However, the scale of these massive networks has shattered the foundation of previous algorithms and inference tools on network data and has necessitated the development of machine learning methods on networks with only a limited amount of available information. In this talk, I will focus on recent advances in this direction in the context of clustering. In more detail, I will talk about some theoretical progress in the context of:
- Spectral algorithms on networks with missing data.
- Graph representation learning algorithms such as DeepWalk/Node2vec.
Dr. Dhara received his PhD from Eindhoven University of Technology in 2018 and is currently a Simons-Berkeley Fellow at the Simons Institute, University of California Berkeley.
Join via Zoom: https://illinois.zoom.us/j/85128211427?pwd=S2QxR0JaMjNXTUYwRThPUDU0S3NOZz09&from=addon