RelBench v2 expands a relational deep learning benchmark with four new large datasets and autocomplete tasks, showing models that use table relationships outperform single-table baselines.
The ctu prague relational learning repository
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
Proposes a pretrained Universal Row Encoder using transformers and global statistics to generate table-width invariant row embeddings for modular relational graph models, claiming improved transfer, convergence, and memory on RelBench.
LMFAO introduces layered logical and code optimizations for shared computation across batches of aggregates, enabling efficient model learning directly over relational data and outperforming commercial databases and ML libraries by orders of magnitude on four datasets.
citing papers explorer
-
RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
RelBench v2 expands a relational deep learning benchmark with four new large datasets and autocomplete tasks, showing models that use table relationships outperform single-table baselines.
-
Joint Relational Database Generation via Graph-Conditional Diffusion Models
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
-
Universal Encoders for Modular Relational Deep Learning
Proposes a pretrained Universal Row Encoder using transformers and global statistics to generate table-width invariant row embeddings for modular relational graph models, claiming improved transfer, convergence, and memory on RelBench.
-
A Layered Aggregate Engine for Analytics Workloads
LMFAO introduces layered logical and code optimizations for shared computation across batches of aggregates, enabling efficient model learning directly over relational data and outperforming commercial databases and ML libraries by orders of magnitude on four datasets.