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.
Jan Motl and Oliver Schulte
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
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.
RelAD detects anomalous entities in relational databases by jointly reconstructing sparse attribute blocks and relation-specific edges, outperforming tabular and homogeneous-graph baselines on six injected-anomaly benchmarks.
RelGT-AC adds column masking, unified task head, and TF-IDF encoding to RelGT, outperforming GraphSAGE on regression autocomplete tasks and gaining up to 10 AUROC on text-heavy tasks across RelBench v2 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.
-
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.
-
Towards Anomaly Detection on Relational Data
RelAD detects anomalous entities in relational databases by jointly reconstructing sparse attribute blocks and relation-specific edges, outperforming tabular and homogeneous-graph baselines on six injected-anomaly benchmarks.
-
RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases
RelGT-AC adds column masking, unified task head, and TF-IDF encoding to RelGT, outperforming GraphSAGE on regression autocomplete tasks and gaining up to 10 AUROC on text-heavy tasks across RelBench v2 datasets.