Relational In-Context Learning via Synthetic Pre-training with Structural Prior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yanbo, You, Jiaxuan, Shi, Chuan, Zhang, Muhan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916060327837696
author Wang, Yanbo
You, Jiaxuan
Shi, Chuan
Zhang, Muhan
author_facet Wang, Yanbo
You, Jiaxuan
Shi, Chuan
Zhang, Muhan
contents Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce, and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, we introduce RDB-PFN, the first relational foundation model trained purely via synthetic data. Inspired by Prior-Data Fitted Networks (PFNs), where synthetic data generated from Structural Causal Models (SCMs) enables reasoning on single tables, we design a Relational Prior Generator to create an infinite stream of diverse RDBs from scratch. Pre-training on over 2 million synthetic single-table and relational tasks, RDB-PFN learns to adapt to any new database instantly via genuine in-context learning. Experiments show that RDB-PFN achieves strong few-shot performance on 19 real-world relational prediction tasks, outperforming state-of-the-art tabular foundation models evaluated on the same DFS-linearized inputs, while using a lightweight architecture and fast inference. The code is available at https://github.com/MuLabPKU/RDBPFN.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03805
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Relational In-Context Learning via Synthetic Pre-training with Structural Prior
Wang, Yanbo
You, Jiaxuan
Shi, Chuan
Zhang, Muhan
Machine Learning
Artificial Intelligence
Databases
Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce, and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, we introduce RDB-PFN, the first relational foundation model trained purely via synthetic data. Inspired by Prior-Data Fitted Networks (PFNs), where synthetic data generated from Structural Causal Models (SCMs) enables reasoning on single tables, we design a Relational Prior Generator to create an infinite stream of diverse RDBs from scratch. Pre-training on over 2 million synthetic single-table and relational tasks, RDB-PFN learns to adapt to any new database instantly via genuine in-context learning. Experiments show that RDB-PFN achieves strong few-shot performance on 19 real-world relational prediction tasks, outperforming state-of-the-art tabular foundation models evaluated on the same DFS-linearized inputs, while using a lightweight architecture and fast inference. The code is available at https://github.com/MuLabPKU/RDBPFN.
title Relational In-Context Learning via Synthetic Pre-training with Structural Prior
topic Machine Learning
Artificial Intelligence
Databases
url https://arxiv.org/abs/2603.03805