Matrix Means for Signed and Multilayer Graph Clustering

Add to your list(s) Download to your calendar using vCal

• Pedro Mercado (University of Tübingen)
• Tuesday 12 November 2019, 13:00-14:00
• SS03, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Mateja Jamnik.

In this talk we present an extension of spectral clustering for the case when different kinds of interactions are present. We study suitable matrix functions to merge information that comes from different kinds of interactions encoded in multilayer graphs, and their effect in cluster identification. We consider a one-parameter family of matrix functions, known as matrix power means, and show that different means identify clusters under different settings of the stochastic block model in expectation. For instance, we show that a limit case identifies clusters if at least one layer is informative and the remaining layers are potentially just noise.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Artificial Intelligence Research Group Talks (Computer Laboratory)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• SS03, Computer Laboratory, William Gates Building
• School of Technology
• Speech Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list

Note that ex-directory lists are not shown.