Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases

• URL: http://arxiv.org/abs/2508.08327v1
• Date: Sun, 10 Aug 2025 07:59:41 GMT
• Title: Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases
• Authors: Ning Li, Kounianhua Du, Han Zhang, Quan Gan, Minjie Wang, David Wipf, Weinan Zhang,
• Abstract summary: We propose SRP, a unified predictive modeling framework that synthesizes features using the unary dependency.<n>SRP is designed to fully capture both the unary and the composite dependencies within a relational database.
• Score: 34.57267286892218
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Relational databases (RDBs) have become the industry standard for storing massive and heterogeneous data. However, despite the widespread use of RDBs across various fields, the inherent structure of relational databases hinders their ability to benefit from flourishing deep learning methods. Previous research has primarily focused on exploiting the unary dependency among multiple tables in a relational database using the primary key - foreign key relationships, either joining multiple tables into a single table or constructing a graph among them, which leaves the implicit composite relations among different tables and a substantial potential of improvement for predictive modeling unexplored. In this paper, we propose SRP, a unified predictive modeling framework that synthesizes features using the unary dependency, retrieves related information to capture the composite dependency, and propagates messages across a constructed graph to learn adjacent patterns for prediction on relation databases. By introducing a new retrieval mechanism into RDB, SRP is designed to fully capture both the unary and the composite dependencies within a relational database, thereby enhancing the receptive field of tabular data prediction. In addition, we conduct a comprehensive analysis on the components of SRP, offering a nuanced understanding of model behaviors and practical guidelines for future applications. Extensive experiments on five real-world datasets demonstrate the effectiveness of SRP and its potential applicability in industrial scenarios. The code is released at https://github.com/NingLi670/SRP.

Related papers

• RelBench v2: A Large-Scale Benchmark and Repository for Relational Data [33.795728412518834]
  We introduce RelBench v2, a major expansion of the RelBench benchmark for RDL.<n>RDL models consistently outperform single-table baselines across autocomplete forecasting, and recommendation tasks.
  arXiv  Detail & Related papers  (2026-02-13T04:23:48Z)
• PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models [51.42043158297229]
  We introduce Pluel, a framework to synthesize multi-tabular relational databases from scratch.<n>In a step-by-step fashion, Pluel models (1) schemas with directed graphs, (2) inter-table primary-foreign key connectivity with bipartite graphs, and, (3) feature distributions in tables via conditional causal mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T21:35:18Z)
• Relational Database Distillation: From Structured Tables to Condensed Graph Data [48.347717300340435]
  We aim to distill large-scale RDBs into compact heterogeneous graphs while retaining the power required for graph-based models.<n>We further design a kernel ridge regression-guided objective with pseudo-labels, which produces quality features for the distilled graph.
  arXiv  Detail & Related papers  (2025-10-08T13:05:31Z)
• A Pre-training Framework for Relational Data with Information-theoretic Principles [57.93973948947743]
  We introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs supervisory signals via set-based aggregation over relational graphs.<n>TVE consistently outperforms traditional pre-training baselines.<n>Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.
  arXiv  Detail & Related papers  (2025-07-14T00:17:21Z)
• Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures [50.46688111973999]
  Graph machine learning has led to a significant increase in the capabilities of models that learn on arbitrary graph-structured data.<n>We present a new blueprint that enables end-to-end representation of'relational entity graphs' without traditional engineering feature.<n>We discuss key challenges including large-scale multi-table integration and the complexities of modeling temporal dynamics and heterogeneous data.
  arXiv  Detail & Related papers  (2025-06-19T23:51:38Z)
• RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models [83.6013616017646]
  RelDiff is a novel diffusion generative model that synthesizes complete relational databases by explicitly modeling their foreign key graph structure.<n>RelDiff consistently outperforms prior methods in producing realistic and coherent synthetic relational databases.
  arXiv  Detail & Related papers  (2025-05-31T21:01:02Z)
• Joint Relational Database Generation via Graph-Conditional Diffusion Models [44.06390394789874]
  Building generative models for databases (RDBs) is important for applications like privacy's data release and real datasets.<n>Most prior either focuses on single-table generation or relies on autoregressive factorizations that impose a fixed table order and generate tables sequentially.<n>We propose a fundamentally different approach: jointly modeling all tables in an RDB without imposing any order.
  arXiv  Detail & Related papers  (2025-05-22T11:12:56Z)
• LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion [49.898152180805454]
  Synthetic datasets must maintain domain-specific logical consistency.<n>Existing generative models often overlook these inter-column relationships.<n>This study presents the first method to effectively preserve inter-column relationships without requiring domain knowledge.
  arXiv  Detail & Related papers  (2025-03-04T00:47:52Z)
• RelBench: A Benchmark for Deep Learning on Relational Databases [78.52438155603781]
  We present RelBench, a public benchmark for solving tasks over databases with graph neural networks. We use RelBench to conduct the first comprehensive study of Deep Learning infrastructure. RDL learns better whilst reducing human work needed by more than an order of magnitude.
  arXiv  Detail & Related papers  (2024-07-29T14:46:13Z)
• IRG: Generating Synthetic Relational Databases using Deep Learning with Insightful Relational Understanding [13.724085637262654]
  We propose incremental generator (IRG) that successfully handles ubiquitous real-life situations.<n>IRG ensures the preservation of relational schema integrity, offers a deep understanding of relationships beyond direct ancestors and descendants.<n> Experiments on three open-source real-life relational datasets in different fields at different scales demonstrate IRG's advantage in maintaining the synthetic data's relational schema validity and data fidelity and utility.
  arXiv  Detail & Related papers  (2023-12-23T07:47:58Z)
• Relational Deep Learning: Graph Representation Learning on Relational Databases [69.7008152388055]
  We introduce an end-to-end representation approach to learn on data laid out across multiple tables. Message Passing Graph Neural Networks can then automatically learn across the graph to extract representations that leverage all data input.
  arXiv  Detail & Related papers  (2023-12-07T18:51:41Z)
• On Embeddings in Relational Databases [11.52782249184251]
  We address the problem of learning a distributed representation of entities in a relational database using a low-dimensional embedding. Recent methods for learning embedding constitute of a naive approach to consider complete denormalization of the database by relationalizing the full join of all tables and representing as a knowledge graph. In this paper we demonstrate; a better methodology for learning representations by exploiting the underlying semantics of columns in a table while using the relation joins and the latent inter-row relationships.
  arXiv  Detail & Related papers  (2020-05-13T17:21:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.