Search Results for author: Ismail Ilkan Ceylan

Found 2 papers, 2 papers with code

Homomorphism Counts for Graph Neural Networks: All About That Basis

1 code implementation13 Feb 2024 Emily Jin, Michael Bronstein, Ismail Ilkan Ceylan, Matthias Lanzinger

In this work, we show that both of these approaches are sub-optimal in a certain sense and argue for a more fine-grained approach, which incorporates the homomorphism counts of all structures in the "basis" of the target pattern.

Learning to Reason: Leveraging Neural Networks for Approximate DNF Counting

1 code implementation4 Apr 2019 Ralph Abboud, Ismail Ilkan Ceylan, Thomas Lukasiewicz

Weighted model counting (WMC) has emerged as a prevalent approach for probabilistic inference.

Cannot find the paper you are looking for? You can Submit a new open access paper.