3 papers
cs.NE2024
Efficient NAS with FaDE on Hierarchical Spaces
Simon Neumeyer, Julian Stier, Michael Granitzer
Neural architecture search (NAS) is a challenging problem. Hierarchical search spaces allow for cheap evaluations of neural network sub modules to serve as surrogate for architectu…
cs.LG2023
GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators
Ousmane Touat, Julian Stier, Pierre-Edouard Portier +1
A wide variety of generative models for graphs have been proposed. They are used in drug discovery, road networks, neural architecture search, and program synthesis. Generating gra…
cs.LG2021
deepstruct -- linking deep learning and graph theory
Julian Stier, Michael Granitzer
deepstruct connects deep learning models and graph theory such that different graph structures can be imposed on neural networks or graph structures can be extracted from trained n…