Incorporating Deep Learning Design in Database Queries

• URL: http://arxiv.org/abs/2605.24207v1
• Date: Fri, 22 May 2026 20:47:07 GMT
• Title: Incorporating Deep Learning Design in Database Queries
• Abstract summary: We propose an approach that naturally integrates deep learning with database queries.<n>We describe RelaNN, a proof-of-concept implementation of this approach built on top of PyTorch and cuDF.
• Score: 3.967959244819106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning over relational databases is conventionally realized by translating data into graph representations and applying graph-based neural networks within external frameworks. This round-trip between the database and external machine learning (ML) systems introduces non-trivial engineering overhead. In effect, these graph neural networks operate on tuple embeddings and manipulate them in ways that capture the interactions induced by relational joins. Given this natural correspondence, there is no fundamental reason why specifying a neural network over relational data should be substantially harder than querying it. We propose an approach that naturally integrates deep learning with database queries. The key idea is to associate each tuple with provenance, represented as a vector embedding with learnable parameters. Queries are lifted to operate jointly on data and embeddings, mapping input relations with embedded tuples to output relations with embedded tuples. This approach provides a declarative foundation for relational deep learning, facilitating integration with database systems, optimization, and wide adoption. We describe RelaNN, a proof-of-concept implementation of this approach built on top of PyTorch and cuDF. We illustrate the utility of RelaNN by implementing various graph-learning models, including graph convolutional networks, heterogeneous graph transformers, hypergraph neural networks and deep homomorphism networks. The simplicity of the programs and their competitive runtime performance demonstrate a concrete path toward making the implementation of state-of-the-art neural networks over databases as simple as writing a query.

Related papers

• Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data [9.932884719997432]
  We introduce Neuro-Relational Programs (NRPs), a declarative query language for relational databases.<n>NRPs extend Datalog-style rules with operations that combine, aggregate, and transform embeddings.<n>We characterize the expressive power of unrestricted NRPs with ReLU-FFN transformations by FOCQ.
  arXiv  Detail & Related papers  (2026-06-10T11:16:36Z)
• 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)
• Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases [3.6423651166048874]
  Flattening the database poses challenges for deep learning models.<n>We propose a novel hypergraph-based framework, that we call rel-HNN.<n>We show that rel-HNN significantly outperforms existing methods in both classification and regression tasks.
  arXiv  Detail & Related papers  (2025-07-16T18:20:45Z)
• 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)
• RelGNN: Composite Message Passing for Relational Deep Learning [56.48834369525997]
  We introduce RelGNN, a novel GNN framework specifically designed to leverage the unique structural characteristics of the graphs built from relational databases.<n>RelGNN is evaluated on 30 diverse real-world tasks from Relbench (Fey et al., 2024), and achieves state-of-the-art performance on the vast majority tasks, with improvements of up to 25%.
  arXiv  Detail & Related papers  (2025-02-10T18:58:40Z)
• 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)
• GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph [53.70520466556453]
  We propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models. With the proposed architecture, the text encoding and the graph aggregation are fused into an iterative workflow. In addition, a progressive learning strategy is introduced, where the model is successively trained on manipulated data and original data to reinforce its capability of integrating information on graph.
  arXiv  Detail & Related papers  (2021-05-06T12:20:41Z)
• Relation-Guided Representation Learning [53.60351496449232]
  We propose a new representation learning method that explicitly models and leverages sample relations. Our framework well preserves the relations between samples. By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
  arXiv  Detail & Related papers  (2020-07-11T10:57:45Z)
• Siamese Graph Neural Networks for Data Integration [11.41207739004894]
  We propose a general approach to modeling and integrating entities from structured data, such as relational databases, as well as unstructured sources, such as free text from news articles. Our approach is designed to explicitly model and leverage relations between entities, thereby using all available information and preserving as much context as possible. We evaluate our method on the task of integrating data about business entities, and we demonstrate that it outperforms standard rule-based systems, as well as other deep learning approaches that do not use graph-based representations.
  arXiv  Detail & Related papers  (2020-01-17T21:51:55Z)

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.