activity
20242026
collaborators

6 papers

cs.PL2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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,…