Search Results for author: Filip Zelezny

Found 5 papers, 4 papers with code

Learning with Molecules beyond Graph Neural Networks

1 code implementation6 Nov 2020 Gustav Sourek, Filip Zelezny, Ondrej Kuzelka

We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures.

Lossless Compression of Structured Convolutional Models via Lifting

2 code implementations ICLR 2021 Gustav Sourek, Filip Zelezny, Ondrej Kuzelka

The computation graphs themselves then reflect the symmetries of the underlying data, similarly to the lifted graphical models.

Knowledge Base Completion

Beyond Graph Neural Networks with Lifted Relational Neural Networks

2 code implementations13 Jul 2020 Gustav Sourek, Filip Zelezny, Ondrej Kuzelka

We demonstrate a declarative differentiable programming framework based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to encode relational learning scenarios.

Relational Reasoning

Stacked Structure Learning for Lifted Relational Neural Networks

no code implementations5 Oct 2017 Gustav Sourek, Martin Svatos, Filip Zelezny, Steven Schockaert, Ondrej Kuzelka

Lifted Relational Neural Networks (LRNNs) describe relational domains using weighted first-order rules which act as templates for constructing feed-forward neural networks.

Lifted Relational Neural Networks

1 code implementation20 Aug 2015 Gustav Sourek, Vojtech Aschenbrenner, Filip Zelezny, Ondrej Kuzelka

We propose a method combining relational-logic representations with neural network learning.

Relational Reasoning

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