Metraipolis › archive › dc_f596352f81e4

Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generation — arXiv:2610.06854

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06854
License (as archived)
CC0-1.0
Archived
2026-10-07T11:42:03.397Z
SHA-256 of the archived text
6afccfb24419ae40506244648f6fd0fcf966a5aeae37be9879c6b6f0babf37a3
Stable URL of this page
https://metraipolis.com/documento/dc_f596352f81e4

How to cite

Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generation — arXiv:2610.06854 — arXiv (en), https://arxiv.org/abs/2610.06854 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f596352f81e4 (Metraipolis archive dc_f596352f81e4, sha256 6afccfb24419ae40506244648f6fd0fcf966a5aeae37be9879c6b6f0babf37a3)
BibTeX
@misc{dcf596352f81e4,
  title = {Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generation — arXiv:2610.06854},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06854},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f596352f81e4; sha256 6afccfb24419ae40506244648f6fd0fcf966a5aeae37be9879c6b6f0babf37a3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06854. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthetic data generation is critical for privacy compliance, machine learning augmentation, and software testing. While single-table evaluation is well established, multi-table (relational) synthesis, the dominant enterprise use case, lacks a unified evaluation framework. Existing approaches assess marginal column distributions in isolation, overlooking joint distributions, cross-table structural integrity, downstream utility, and production-readiness edge cases. We present SynEval, a six-dimensional evaluation framework for multi-table synthetic databases. SynEval jointly assesses per-column fidelity, multivariate structure preservation including a novel conditional distribution check, cross-table integrity, ML utility, privacy protection, and edge-case robustness. The framework produces a unified weighted quality score with per-table and per-dimension drill-down, and is generator-agnostic, operating on any pair of real and synthetic CSV folders with automatic schema inference. SynEval is a framework to combine conditional distribution checks P(Y|X), cross-table cardinality validation, and production-readiness edge-case testing within a single evaluation pipeline for relational synthetic data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06854 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:19:24.856Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).