Persons
Ing. Peter Jung
All publications
Graph Generation with Graphon Generative Adversarial Networks
- Authors: Ing. Peter Jung, Ing. Ondřej Kuželka, Ph.D.,
- Publication: Proceedings of The 31st International Conference on Inductive Logic Programming. Proceedings of Machine Learning Research, 2022.
- Year: 2022
- Department: Department of Computer Science, Intelligent Data Analysis
-
Annotation:
Graphons are limits of converging sequences of graphs with a particularly simple representation—a graphon is simply a symmet ric function of two variables on [0; 1]2. In this work, we develop an el- egant GAN model, called GraphonGAN, which uses graphons imple- mented by neural networks as generators and graph neural networks as discriminators. We show that GraphonGAN is a decent model for modelling real-world networks. All the source codes will be available at https://github.com/kongzii/gangraphon
Learning to Generate Molecules From Small Datasets Using Neural Markov Logic Networks
- Authors: Ing. Martin Svatoš, Ing. Peter Jung, prof. Ing. Filip Železný, Ph.D., Marra, G., Ing. Ondřej Kuželka, Ph.D.,
- Publication: International Joint Conference on Learning & Reasoning. Cham: Springer, 2022.
- Year: 2022
- Department: Department of Computer Science, Intelligent Data Analysis
-
Annotation:
Neural Markov Logic networks are a statistical relational model capable of generating relational structures. In this paper, we investigate how this particular model behaves in the setup of few-shot learning and show that Neural Markov Logic Networks are able to learn to generate small molecules from a handful of training examples without any pre-training.