research
∙
10/21/2022
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
Graph neural networks (GNNs) are able to leverage the structure of graph...
share
research
∙
08/06/2022
Oversquashing in GNNs through the lens of information contraction and graph expansion
The quality of signal propagation in message-passing graph neural networ...
research
∙
04/23/2022
Continuity and Additivity Properties of Information Decompositions
Information decompositions quantify how the Shannon information about a ...
research
∙
10/23/2021
Learning curves for Gaussian process regression with power-law priors and targets
We study the power-law asymptotics of learning curves for Gaussian proce...
research
∙
05/04/2021
Information Complexity and Generalization Bounds
We present a unifying picture of PAC-Bayesian and mutual information-bas...
research
∙
01/23/2019
Unique Information and Secret Key Decompositions
The unique information (UI) is an information measure that quantifies a ...
research
∙
10/27/2018
The Variational Deficiency Bottleneck
We introduce a bottleneck method for learning data representations based...
research
∙
07/13/2018