TabStruct: Measuring Structural Fidelity of Tabular Data

ICLROral2026

Authors
Xiangjian Jiang, Nikola Simidjievski, Mateja Jamnik
Affiliation
University of Cambridge
Venue
ICLR 2026
Track
Oral

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.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

benchmark tabular causal

← All ICLR 2026 Oral papers · Browse the whole archive