M
Martin Ritzert
Researcher at RWTH Aachen University
Publications - 18
Citations - 1232
Martin Ritzert is an academic researcher from RWTH Aachen University. The author has contributed to research in topics: Computer science & Time complexity. The author has an hindex of 6, co-authored 15 publications receiving 564 citations.
Papers
More filters
Journal ArticleDOI
Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks
Christopher Morris,Martin Ritzert,Matthias Fey,William L. Hamilton,Jan Eric Lenssen,Gaurav Rattan,Martin Grohe +6 more
TL;DR: In this article, a generalization of GNNs, called k-dimensional GNN (k-GNNs), is proposed, which can take higher-order graph structures at multiple scales into account.
Posted Content
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
Christopher Morris,Martin Ritzert,Matthias Fey,William L. Hamilton,Jan Eric Lenssen,Gaurav Rattan,Martin Grohe +6 more
TL;DR: In this article, a generalization of GNNs, called $k$-dimensional GNN, was proposed, which can take higher-order graph structures at multiple scales into account.
Posted Content
Graph Neural Networks for Maximum Constraint Satisfaction
TL;DR: This work introduces a graph neural network architecture that works for all binary constraint satisfaction problems and matches or surpasses most greedy and semi-definite programming based algorithms and sometimes even outperforms state-of-the-art heuristics for the specific problems.
Proceedings ArticleDOI
Learning first-order definable concepts over structures of small degree
Martin Grohe,Martin Ritzert +1 more
TL;DR: In this paper, a declarative framework for machine learning where concepts and hypotheses are defined by formulas of a logic over some "background structure" is considered, and it is shown that concepts defined by first-order formulas over a background structure of at most polylogarithmic degree can be learned in polylogrithmic time.
Posted Content
Learning first-order definable concepts over structures of small degree
Martin Grohe,Martin Ritzert +1 more
TL;DR: This work considers a declarative framework for machine learning where concepts and hypotheses are defined by formulas of a logic over some “background structure” and shows that concepts defined by first-order formulas over a background structure can be learned in polylogarithmic time in the “probably approximately correct” learning sense.