Publications (9)
When do neural ordinary differential equations generalize on complex networks?
Moritz Laber, Tina Eliassi-Rad, Brennan Klein
Neural ordinary differential equations (neural ODEs) can effectively learn dynamical systems from time series data, but their behavior on graph-structured data remains poorly under…
Deterministic construction of typical networks in network models
Narayan G. Sabhahit, Moritz Laber, Harrison Hartle +4
It is often desirable to assess how well a given dataset is described by a given model. In network science, for instance, one often wants to say that a given real-world network app…
A Guide to Higher-Order Homophily
Moritz Laber, Brennan Klein
Homophily, the overrepresentation of interactions among similar individuals, and heterophily, the elevated prevalence of interactions among dissimilar ones, are frequently observed…
Adaptive Shock Compensation in the Multi-layer Network of Global Food Production and Trade
Sophia Baum, Moritz Laber, Martin Bruckner +3
Global food production and trade networks are highly dynamic, especially in response to shortages when countries adjust their supply strategies. In this study, we examine adjustmen…
Multi-strain spreading dynamics under arbitrary transmission kernels
Sagar Kumar, Moritz Laber, Maimuna S. Majumder +2
Compartmental models of epidemic dynamics have long described the propagation of a single, immutable transmissible state through a population via pairwise contact, and multi-strain…
Identifying and Upweighting Power-Niche Users to Mitigate Popularity Bias in Recommendations
David Liu, Erik Weis, Moritz Laber +2
Recommender systems have been shown to exhibit popularity bias by over-recommending popular items and under-recommending relevant niche items. We seek to understand niche users in…