Tag
The article discusses desired features for a modern relational query language, critiquing SQL's shortcomings and suggesting improvements based on functional programming, better syntax, and user-defined types.
Presents Doc2DB-Bench, a benchmark for evaluating LLM-based extraction of relational databases from long documents, with 203 instances across 42 schemas and seven domains.
This paper explores using the PluRel synthetic relational database generator as an external data source for pretraining RDB-PFN, a relational in-context learner, demonstrating that schema-guided curriculum design can recover most of the original performance with far fewer pretraining tasks.
This paper argues that parameter-free encoders remain viable for relational database foundation models, providing theoretical limitations on trainable encoder parameters and empirical validation across benchmarking tasks.
This paper introduces RelAD, a reconstruction-based framework for detecting anomalies in relational databases by jointly modeling attribute and relational edge reconstruction. Extensive experiments on six new benchmarks show RelAD outperforms existing methods.
This paper introduces RelGT-AC, a relational graph transformer architecture tailored for autocomplete tasks in relational databases. The model extends the RelGT architecture with column masking to prevent trivial solutions, a unified task head for multiple prediction types, and a TF-IDF text encoder to leverage lexical signals, achieving significant improvements over baselines on RelBench v2 benchmarks.
This paper explores the expressive power of Deep Homomorphism Networks (DHNs) for learning over relational databases, linking them to fragments of first-order logic and SQL, and analyzing static analysis problems like emptiness and subsumption.