Tackling Unknown Connectivity: Latent Graph and Latent Topology Inference and its Applications

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

• Lev Telyatnikov, Dept of Computer Science, La Sapienza, University of Roma 1
• Friday 04 August 2023, 17:00-18:00
• Lecture Theatre 2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Pietro Lio.

This talk has been canceled/deleted

Graph data, like any other type of data, is susceptible to imperfections. Specifically, edge sets may contain various issues, such as noise and incompleteness, which have been extensively studied. However, in extreme scenarios, the edge set may be entirely unknown, implying the impossibility of applying graph neural networks. The problem of unknown connectivity can be framed from the perspective that any type of data has an underlying graph topology that can be learned to boost the performance of downstream tasks.

This talk is part of the Foundation AI series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.