Relational Databases

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 26

All topics

RelICL: Training-free Relational Learning with Tabular Foundation Models
Oct 1, 2026Simon Forbat, Rainer GemullaRelational Deep Learning Relational Databases
Data and Web Science Group University of Mannheim Mannheim, Germany
JoinGR: Learning to Traverse Join Graphs for Table Retrieval
Oct 1, 2026Sandipan De, Abhijit Chakraborty, Sambaran Bandyopadhyay +1Graph-Based Retrieval Relational Databases
Arizona State University · Adobe Research, India
STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling
Oct 1, 2026Abdalla Mohamed, Ashraf AboulnagaRelational Databases Inference Cost
University of Texas at Arlington
Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Model Dependence and Evaluation Reliability
Sep 29, 2026Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer +6Relational Deep Learning Relational Databases
SAP Palo Alto, CA, USA · SAP Montreal, Canada · SAP Seattle, WA, USA
Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Impact, Detection, and Mitigation
Sep 28, 2026Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer +5Relational Databases In-Context Learning
SAP
InRTL: Effective Intra-Inter Interaction Learning for Relational Tables
Sep 14, 2026Weichen Li, Ken Zhong, Zheng Wang +2Relational Databases Tabular Data
Shanghai Jiao Tong University Shanghai, China
Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data
Sep 1, 2026Gene ZhangRelational Databases Graph Representations
System: ClickGraph / DeltaGraph
Context Window Failures in Relational Foundation Models
Aug 31, 2026Denis Oliveira Correa, Francisco Galuppo AzevedoRelational Databases Foundation Model
Kunumi Institute, Brazil · Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil.
TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning
Jul 28, 2026Rwaida Alssadi, Muntaser Syed, Balaji Kasula +6Code Generation Model Auditing
Florida Institute of Technology
SINT-Flow: Schema Integration using Large Language Model Workflows
Jul 27, 2026Keti Korini, Christian BizerSchema Relational Databases
University of Mannheim Mannheim, Germany
Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation
Jul 10, 2026Konrad Özdemir, Julia Gastinger, Lukas Kirchdorfer +1Temporal Knowledge Graphs Distribution Shifts
Data and Web Science Group, University of Mannheim, Germany · SAP Signavio, Walldorf, Germany
Parameter-Free Encoders Remain Viable for RDB Foundation Models
Jul 6, 2026Linjie Xu, David WipfTabular Foundation Models Sentence Encoders
University of Hong Kong, Shanghai X-Lab.
A Fair Benchmarking of Deep Relational Database Learning Models
Jul 4, 2026Kazi F. Akhter, Bharath Ajendla, Manar D. SamadRelational Deep Learning Relational Databases
Department of Computer Science Tennessee State University Nashville, TN, USA · SAP AI Research and Innovation SAP Labs Palo Alto, CA, USA
Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation
May 29, 2026Madhav Jivrajani, Ramnatthan Alagappan, Aishwarya GanesanText-To-Sql Agentic Discovery
University of Illinois Urbana-Champaign
RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
May 22, 2026Jinyu Yang, Cheng Yang, Junze Chen +4Relational Deep Learning Relational Databases
Beijing University Of Posts and Telecommunications Beijing, China · Peng Cheng Laboratory Shenzhen, China · China Telecom Bestpay Beijing, China +1
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
May 20, 2026Yi Huang, Qingyun Sun, Jia Li +2Relational Deep Learning Relational Databases
SKLCCSE, School of Computer Science and Engineering, Beihang University, Beijing, China · Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China
On the Complexity of Entailment for Cumulative Propositional Dependence Logics
May 20, 2026Kai Sauerwald, Juha Kontinen, Arne MeierLogic Entailment
FernUniversität in Hagen, Hagen, Germany · University of Helsinki, Helsinki, Finland · Leibniz Universität Hannover, Hannover, Germany
Expressive Power of Deep Homomorphism Networks over Relational Databases
May 18, 2026Moritz Schönherr, Balder ten Cate, Maurice Funk +3Relational Deep Learning Relational Databases
Leipzig University · University of Amsterdam · Technion & RelationalAI
Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
May 15, 2026Jingcheng Wu, Ratan Bahadur Thapa, Mojtaba Nayyeri +4Relational Deep Learning Relational Databases
University of Stuttgart, Stuttgart, Germany · Web and Internet Science Research Group, University of Southampton, Southampton, United Kingdom
On the Limitations of Large Language Models for Conceptual Database Modeling
May 12, 2026Arthur F. Siqueira, Carlos D. S. Nogueira, Eduarda Farias +2Relational Databases Diagrams
1Systems and Computing Department Federal University of Campina Grande (UFCG)2026 Campina Grande – PB – Brazil
Template-as-Ontology: Configurable Synthetic Data Infrastructure for Cross-Domain Manufacturing AI Validation
May 11, 2026Grama ChethanSynthetic Data Ontology
Siemens Digital Industries Software, Plano, TX 75024, United States
CORE: Cyclic Orthotope Relation Embedding for Knowledge Graph Completion
May 11, 2026Yingqi Zeng, Luying Wang, Huiling ZhuKnowledge Graph Completion Zero-Shot Link Prediction
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration
Apr 18, 2026Chongsheng Zhang, Hao Wang, Zelong Yu +7Synthetic Tabular Data Synthetic Data
Henan University, China · Department of Statistics, LMU Munich · MCML Munich +1
PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
Feb 3, 2026Vignesh Kothapalli, Rishabh Ranjan, Valter Hudovernik +4Relational Databases Synthetic Data
1Stanford University · 2Kumo AI · 3SAP Labs LLC
Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
Nov 29, 2025Ashish Thanga, Vibhu Dixit, Abhilash Shankarampeta +1Schema Relational Databases
Arizona State University · UC San Diego
Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts
May 29, 2024Lanting Fang, Yulian Yang, Yawei Zhang +3Physics-Guided Diffusion Causal Discovery Methods
1Beijing Institue of Technology · Southeast University · Wuhan University

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

RelICL: Training-free Relational Learning with Tabular Foundation Models

Simon Forbat, Rainer Gemulla

Data and Web Science Group University of Mannheim Mannheim, Germany

Relational Deep Learning Relational Databases Tabular Foundation Models Relational Tabular Data

Open paper AskPDF arXiv

Tabular foundation models achieve state-of-the-art performance on single-table tasks without any training. Recent work suggests that they are also well-suited for relational learning via deep feature synthesis (DFS), which flattens a relational schema into a single table by adding aggregates of the other tables' columns as features. This approach is appealing because it directly benefits from improvements to or customization of the underlying tabular foundation model. In this paper, we identify two key problems with DFS: feature explosion and interaction blindness. The first problem arises because the number of DFS features grows quickly as the schema becomes more complex, limiting scalability and performance. The second problem arises because column-wise aggregates do not account for feature interactions, limiting performance. We propose and explore an alternative method termed RelICL, which keeps the benefits of DFS but alleviates these two problems. At its heart, RelICL propagates and fuses information step by step through the schema graph, using the same tabular foundation model that is eventually used for prediction to do so. In our experimental study using RelBench tasks, RelICL was on par with the strongest approach based on deep feature synthesis.

Momentum

Related topics

Latest papers 26