8 papers
Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data
Arie Soeteman, Balder ten Cate, Maurice Funk +3
The conventional approach to deep learning over relational databases applies neural models, such as Graph Neural Networks (GNNs), to a graph representation of the database. Recent…
Expressive Power of Deep Homomorphism Networks over Relational Databases
Moritz Schönherr, Balder ten Cate, Maurice Funk +3
The expressive limitations of message-passing Graph Neural Networks (GNNs) have motivated a wide range of more powerful graph learning architectures. We advocate Deep Homomorphism…
Bounded Fitting for Expressive Description Logics
Maurice Funk, Jean Christoph Jung, Tom Voellmer
Bounded fitting is an attractive paradigm for learning logical formulas from labeled data examples that offers PAC-style generalization guarantees and can often be implemented leve…
Towards Understanding the Expressive Power of GNNs with Global Readout
Maurice Funk, Daumantas Kojelis
We study the expressive power of message-passing aggregate-combine-readout graph neural networks (ACR-GNNs). Particularly, we focus on the first-order (FO) properties expressible b…
Expressive Power of Graph Transformers via Logic
Veeti Ahvonen, Maurice Funk, Damian Heiman +2
Transformers are the basis of modern large language models, but relatively little is known about their precise expressive power on graphs. We study the expressive power of graph tr…
Extremal Fitting Problems for Conjunctive Queries
Balder ten Cate, Victor Dalmau, Maurice Funk +1
The fitting problem for conjunctive queries (CQs) is the problem to construct a CQ that fits a given set of labeled data examples. When a fitting CQ exists, it is in general not un…