TabStruct: Measuring Structural Fidelity of Tabular Data

Xiangjian Jiang, Nikola Simidjievski, Mateja Jamnik

Keywords: tabular data, synthetic data generation, tabular data structure

TL;DR: We propose TabStruct, a comprehensive benchmark, along with a novel metric, global utility, for evaluating the structural fidelity of tabular data without requiring access to ground-truth causal structures.

Abstract: Evaluating tabular generators remains a challenging problem, as the unique causal structural prior of heterogeneous tabular data does not lend itself to intuitive human inspection. Recent work has introduced structural fidelity as a tabular-specific evaluation dimension to assess whether synthetic data complies with the causal structures of real data. However, existing benchmarks often neglect the interplay between structural fidelity and conventional evaluation dimensions, thus failing to provide a holistic understanding of model performance. Moreover, they are typically limited to toy datasets, as quantifying existing structural fidelity metrics requires access to ground-truth causal structures, which is rarely available for real-world datasets. In this paper, we propose a novel evaluation framework that jointly considers structural fidelity and conventional evaluation dimensions. We introduce a new evaluation metric, *global utility*, which enables the assessment of structural fidelity even in the absence of ground-truth causal structures. In addition, we present *TabStruct*, a comprehensive evaluation benchmark offering large-scale quantitative analysis on 13 tabular generators from nine distinct categories, across 29 datasets. Our results demonstrate that global utility provides a task-independent, domain-agnostic lens for tabular generator performance. We release the TabStruct benchmark suite, including all datasets, evaluation pipelines, and raw results.

Code URL: https://anonymous.4open.science/r/TabStruct-E4E4

Primary Area: Datasets & Benchmarks illustrating Different Deep learning Scenarios (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 267