Lifted Relational Neural Networks

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

• Gustav Šir, Czech Technical University in Prague
• Tuesday 17 May 2022, 13:15-14:15
• Zoom.

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

Join us on Zoom

Lifted Relational Neural Networks (LRNNs) were introduced as a framework for combining logic programming with neural networks for efficient learning of latent relational structures, such as various subgraph patterns in molecules. In this talk, we will re-introduce the framework in the context of modern Graph Neural Networks (GNNs). Particularly, we will showcase how the declarative nature of (differentiable) logic programming in LRN Ns can be used to elegantly capture the principles of various GNN variants, and extrapolate to other deep relational learning concepts. Additionally, we will overview some applications, computational performance and practical usage of the framework.

BIO: Gustav is a fresh AI/ML post-doc at Czech Technical University. Previously, he did some internships at University of York, Google and IBM research. He focuses on combining relational logic with deep learning.

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
• School of Technology
• Speech Seminars
• Trust & Technology Initiative - interesting events
• Zoom
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list

Note that ex-directory lists are not shown.