6 papers
Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learning
Oleksii Kolesnichenko, Jakub Peleška, Gustav Š\'ır
Relational Deep Learning (RDL) has become a powerful paradigm for learning from multi-tabular data. However, manually defining RDL prediction tasks is a laborious process that freq…
Incremental Evaluation and Training in Relational Deep Learning
Jakub Peleška, Gustav Šír
Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, prevailing RDL evaluation prac…
Universal Encoders for Modular Relational Deep Learning
Jakub Peleška, Gustav Šír
Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation learning. While RDL is evolving rapidly, existing appro…
Task-Agnostic Contrastive Pretraining for Relational Deep Learning
Jakub Peleška, Gustav Šír
Relational Deep Learning (RDL) is an emerging paradigm that leverages Graph Neural Network principles to learn directly from relational databases by representing them as heterogene…
REDELEX: A Framework for Relational Deep Learning Exploration
Jakub Peleška, Gustav Šír
Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant…
Transformers Meet Relational Databases
Jakub Peleška, Gustav Šír
Transformer models have continuously expanded into all machine learning domains convertible to the underlying sequence-to-sequence representation, including tabular data. However,…