paper-with-me

Papers

Supervised Learning on Relational Databases with Graph Neural Networks

2020-02-06 · Milan Cvitkovic

The majority of data scientists and machine learning practitioners use relational data in their work [State of ML and Data Science 2017, Kaggle, Inc.]. But training machine learning models on data stored in relational databases requires significant data extraction and feature engineering efforts. These efforts are not only costly, but they also destroy potentially important relational structure in the data. We introduce a method that uses Graph Neural Networks to overcome these challenges. Our proposed method outperforms state-of-the-art automatic feature engineering methods on two out of three datasets.

📄 PDF Abstract BibTeX arXiv:2002.02046

Code (1)

mwcvitkovic/Supervised-Learning-on-Relational-Databases-with-GNNs 공식 구현 pytorch

Tasks

BIG-bench Machine LearningFeature Engineering

Similar Papers 제목 키워드 기반

Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks

2026-05-15 · Jingcheng Wu, Ratan Bahadur Thapa, Mojtaba Nayyeri, Lucas Etteldorf 외 arxiv

Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as convention…

Feature Engineering

GFS: Graph-based Feature Synthesis for Prediction over Relational Databases

2023-12-04 · Han Zhang, Quan Gan, David Wipf, Weinan Zhang

Relational databases are extensively utilized in a variety of modern information system applications, and they always carry valuable data patterns. There are a huge number of data mining or machine learning tasks conduct…

Feature EngineeringInductive Bias

Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders

2022-11-30 · Ciro Antonio Mami, Andrea Coser, Eric Medvet, Alexander T. P. Boudewijn 외

Synthetic data generation has recently gained widespread attention as a more reliable alternative to traditional data anonymization. The involved methods are originally developed for image synthesis. Hence, their applica…

Image GenerationSynthetic Data Generation

RelGNN: Composite Message Passing for Relational Deep Learning

2025-02-10 · Tianlang Chen, Charilaos Kanatsoulis, Jure Leskovec

Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational Deep Learning (RDL) encodes relational da…

Deep LearningGraph Attention

Flaky Performances when Pretraining on Relational Databases

2022-11-09 · Shengchao Liu, David Vazquez, Jian Tang, Pierre-André Noël

We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extracted from relational databases (RDBs). Intuitively, this joint use of SSL and GN…

Graph Neural NetworkLinear evaluationSelf-Supervised Learning