Supervised Learning on Relational Databases with Graph Neural Networks
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.
Code (1)
Tasks
BIG-bench Machine LearningFeature EngineeringSimilar Papers 제목 키워드 기반
Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
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 EngineeringGFS: Graph-based Feature Synthesis for Prediction over Relational Databases
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 BiasGenerating Realistic Synthetic Relational Data through Graph Variational Autoencoders
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 GenerationRelGNN: Composite Message Passing for Relational Deep Learning
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 AttentionFlaky Performances when Pretraining on Relational Databases
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