Universal Encoders for Modular Relational Deep Learning

• URL: http://arxiv.org/abs/2606.21434v1
• Date: Fri, 19 Jun 2026 13:49:47 GMT
• Title: Universal Encoders for Modular Relational Deep Learning
• Abstract summary: Deep Learning (DL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation.<n>Existing approaches face significant obstacles.<n>We propose a modular approach that decouples row encoding from graph message-passing.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation learning. While RDL is evolving rapidly, existing approaches face significant generalization obstacles. They are either schema-specific, requiring training from scratch for every new database, or they rely on monolithic architectures that entangle feature encoding with graph message-passing. Analyzing these limitations, we establish four core pillars for building foundational relational models: semantic granularity, structural topology, temporal causality, and unified optimization. Addressing these pillars, we propose a modular approach that decouples row encoding from graph message-passing. We introduce the Universal Row Encoder, a transformer-based module that integrates raw cell data with schema metadata$-$including column semantics, table names, and global distribution statistics$-$to produce table-width invariant row embeddings. By explicitly feeding global statistics to an intra-row self-attention mechanism, the encoder natively contextualizes unseen features and handles sparse data. Serving as a flexible "backend" for any downstream graph architecture, our pretrained encoder enhances cross-database knowledge transfer on the established RelBench benchmarks while improving learning convergence and memory footprint.

Related papers

• RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases [49.47033473074821]
  We propose RelPrism, a multi-faceted self-supervised learning framework for RDBs.<n>RDB tasks often require multi-faceted information across different perspectives and granularities.<n>Our experiments show that RelPrism improves ROC-AUC by 4.15% for classification and reduces MAE by 10.75% for regression over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-22T05:19:58Z)
• Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning [34.501460016762756]
  FullResolution Structure and Optimizable Graph framework for RDL formulates learning structure as learnable table role modeling problem.<n>We introduce dependency constraints that regularize functional representations across table entity levels.<n>Experiments demonstrate that our method outperforms existing approaches.
  arXiv  Detail & Related papers  (2026-05-20T17:56:09Z)
• Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs [81.43302841109349]
  Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs)<n>We propose an automated multi-agent framework to reconstruct the evolutionary graph of dataset development.
  arXiv  Detail & Related papers  (2026-04-12T06:24:07Z)
• 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)
• Database Views as Explanations for Relational Deep Learning [7.126902744514975]
  We present a novel framework for explaining machine-learning models over relational databases.<n>We develop algorithms that avoid the exhaustive search over the space of all databases.<n>Our approach is evaluated through an extensive empirical study on the RelBench collection.
  arXiv  Detail & Related papers  (2025-09-11T14:11:48Z)
• 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)
• Retrieval-Augmented Generation of Ontologies from Relational Databases [13.160850863758]
  We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies.<n>An approach that turns relationals into rich schemas with minimal human effort is presented.
  arXiv  Detail & Related papers  (2025-06-02T01:10:05Z)
• 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)
• Relational Graph Transformer [44.56132732108148]
  Graph Transformer (Relel) is the first graph transformer designed specifically for relational tables.<n>Relel employs a novel multi-element tokenization strategy that decomposes each node into five components.<n>Our architecture combines local attention over sampled subgraphs with global attention to learnable centroids.
  arXiv  Detail & Related papers  (2025-05-16T07:51:58Z)
• Griffin: Towards a Graph-Centric Relational Database Foundation Model [37.09648739513178]
  Griffin is the first foundation model attemptation designed specifically for Databases (RDBs)<n>We enhance the architecture by incorporating a cross-attention module and a novel aggregator.<n>Griffin is evaluated on large-scale, heterogeneous, and temporal graphs extracted from RDBs across various domains.
  arXiv  Detail & Related papers  (2025-05-08T18:03:43Z)
• Serving Deep Learning Model in Relational Databases [70.53282490832189]
  Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains. We highlight three pivotal paradigms: The state-of-the-art DL-centric architecture offloads DL computations to dedicated DL frameworks. The potential UDF-centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS)
  arXiv  Detail & Related papers  (2023-10-07T06:01:35Z)

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.