RelBench
PulseAugur coverage of RelBench — every cluster mentioning RelBench across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New MoREGT architecture improves cross-database generalization for predictive models
Researchers have developed MoREGT, a novel mixture-of-relational-experts graph transformer designed to improve cross-database generalization for predictive models. This architecture represents rows and cells as tokens, …
-
Simple baselines match complex models in relational deep learning
Researchers have revisited simple baseline methods for relational deep learning, which represents relational databases as temporal heterogeneous graphs. Their study focused on exploiting target attributes, relational at…
-
New RT-J model offers context-efficient predictions on relational data
Researchers have introduced RT-J, a new 85-million-parameter relational foundation model (RFM) designed for context-efficient predictions on tabular and relational data. This model demonstrates accurate forecasting with…
-
New Relational Foundation Model RT-J Achieves Context-Efficient Predictions
Researchers have developed RT-J, an 86-million parameter relational foundation model designed for context-efficient predictions on tabular and relational data. This model requires significantly fewer examples to achieve…
-
Research questions effectiveness of relational embeddings in LLMs
A new research paper explores the integration of relational encoder embeddings into large language models (LLMs) by injecting them as soft tokens into Qwen3.5-4B. The study found that this hybrid approach did not consis…
-
MetaSieve speeds up relational deep learning with SQL-based metapath selection
Researchers have developed MetaSieve, a novel layer designed to accelerate Relational Deep Learning (RDL) by optimizing subgraph selection. MetaSieve leverages SQL queries to analyze database statistics and identify inf…
-
New attacks probe adversarial robustness of relational deep learning pipelines
Researchers have developed new methods to test the adversarial robustness of Relational Deep Learning (RDL) pipelines, which are commonly used for machine learning on relational databases. These pipelines encode databas…
-
New hybrid model enhances relational database processing with LLMs and GNNs
Researchers have developed a novel hybrid architecture that combines a fine-tuned BART language model with a GraphSAGE-based Graph Neural Network (GNN) to better process relational database information. This approach ai…