ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models

TL;DR

ClavaDDPM is a new diffusion-based model that effectively synthesizes complex multi-relational tabular data by capturing long-range dependencies and relationships across multiple tables, outperforming existing methods.

Contribution

It introduces a clustering-guided diffusion model that models inter-table relationships and long-range dependencies efficiently in multi-relational data synthesis.

Findings

Outperforms existing methods on multi-table datasets

Effectively captures long-range dependencies across tables

Maintains competitive utility metrics for single-table data

Abstract

Recent research in tabular data synthesis has focused on single tables, whereas real-world applications often involve complex data with tens or hundreds of interconnected tables. Previous approaches to synthesizing multi-relational (multi-table) data fall short in two key aspects: scalability for larger datasets and capturing long-range dependencies, such as correlations between attributes spread across different tables. Inspired by the success of diffusion models in tabular data modeling, we introduce $\textbf{C}luster$ $\textbf{La}tent$ $\textbf{Va}riable$ $guided$ $\textbf{D}enoising$ $\textbf{D}iffusion$ $\textbf{P}robabilistic$ $\textbf{M}odels$ (ClavaDDPM). This novel approach leverages clustering labels as intermediaries to model relationships between tables, specifically focusing on foreign key constraints. ClavaDDPM leverages the robust generation capabilities of diffusion models while incorporating efficient algorithms to propagate the learned latent variables across tables. This enables ClavaDDPM to capture long-range dependencies effectively. Extensive evaluations on multi-table datasets of varying sizes show that ClavaDDPM significantly outperforms existing methods for these long-range dependencies while remaining competitive on utility metrics for single-table data.