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.
Relbench v2: A large-scale benchmark and repository for relational data
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger models and relational foundation models, scalable and realistic benchmarks are essential for enabling systematic evaluation and progress. In this paper, we introduce RelBench v2, a major expansion of the RelBench benchmark for RDL. RelBench v2 adds four large-scale relational datasets spanning scholarly publications, enterprise resource planning, consumer platforms, and clinical records, increasing the benchmark to 11 datasets comprising over 22 million rows across 29 tables. We further introduce autocomplete tasks, a new class of predictive objectives that require models to infer missing attribute values directly within relational tables while respecting temporal constraints, expanding beyond traditional forecasting tasks constructed via SQL queries. In addition, RelBench v2 expands beyond its native datasets by integrating external benchmarks and evaluation frameworks: we translate event streams from the Temporal Graph Benchmark into relational schemas for unified relational-temporal evaluation, interface with ReDeLEx to provide uniform access to 70+ real-world databases suitable for pretraining, and incorporate 4DBInfer datasets and tasks to broaden multi-table prediction coverage. Experimental results demonstrate that RDL models consistently outperform single-table baselines across autocomplete, forecasting, and recommendation tasks, highlighting the importance of modeling relational structure explicitly.
citation-role summary
dataset 1
citation-polarity summary
years
2026 6roles
dataset 1polarities
use dataset 1representative citing papers
The Rule Violation Score (RVS) is proposed to quantify logical rule compliance of predictive models on relational data, with automatic SQL computation for Horn rules, and shown to distinguish models that accuracy metrics treat as equivalent.
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.
KumoRFM-2 pre-trains on synthetic and real relational data across row, column, foreign-key and cross-sample axes, injects task information early, and achieves up to 8% gains over supervised baselines on 41 benchmarks in few-shot and fine-tuned regimes while handling billion-scale datasets.
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.
RelAgent uses an LLM agent to autonomously generate SQL feature programs paired with classical models for interpretable relational learning predictions that execute efficiently on standard databases.
citing papers explorer
-
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.
-
Beyond Accuracy: Measuring Logical Compliance of Predictive Models
The Rule Violation Score (RVS) is proposed to quantify logical rule compliance of predictive models on relational data, with automatic SQL computation for Horn rules, and shown to distinguish models that accuracy metrics treat as equivalent.
-
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.
-
KumoRFM-2: Scaling Foundation Models for Relational Learning
KumoRFM-2 pre-trains on synthetic and real relational data across row, column, foreign-key and cross-sample axes, injects task information early, and achieves up to 8% gains over supervised baselines on 41 benchmarks in few-shot and fine-tuned regimes while handling billion-scale datasets.
-
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.
-
RelAgent: LLM Agents as Data Scientists for Relational Learning
RelAgent uses an LLM agent to autonomously generate SQL feature programs paired with classical models for interpretable relational learning predictions that execute efficiently on standard databases.