Metraipolis › archive › dc_227844273dad

Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation — arXiv:2609.15284

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15284
License (as archived)
CC0-1.0
Archived
2026-10-16T00:11:35.522Z
SHA-256 of the archived text
ab6341c63aa76ecd1d10ae98523eae9de4f00bc0e0d9d97a8c1b15874284bd77
Stable URL of this page
https://metraipolis.com/documento/dc_227844273dad

How to cite

Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation — arXiv:2609.15284 — arXiv (en), https://arxiv.org/abs/2609.15284 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_227844273dad (Metraipolis archive dc_227844273dad, sha256 ab6341c63aa76ecd1d10ae98523eae9de4f00bc0e0d9d97a8c1b15874284bd77)
BibTeX
@misc{dc227844273dad,
  title = {Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation — arXiv:2609.15284},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15284},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_227844273dad; sha256 ab6341c63aa76ecd1d10ae98523eae9de4f00bc0e0d9d97a8c1b15874284bd77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15284. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Missing values are ubiquitous in heterogeneous data mining, where numerical, categorical, and binary variables often coexist. Many imputation methods, especially diffusion-based ones, treat discrete variables through continuous surrogates such as one-hot relaxations rather than modeling them natively. This creates a mismatch between the model state space and the mixed discrete and continuous structure of the data. We propose Impute-EM, an Expectation Maximization style framework that alternates between imputing missing entries with the current model and refitting a diffusion backbone on completed data. We instantiate Impute-EM with native mixed-state diffusion backbones for heterogeneous data, combining Gaussian and masked categorical components without one-hot relaxations. In exact settings, we characterize the update and show that the observed mask-indexed marginals match the targets at the limit, while making explicit that the full data distribution is generally non-identifiable from incomplete observations alone. Empirically, Impute-EM delivers the best distributional fidelity on mixed-type tabular imputation, on which downstream modeling relies, with text imputation serving as a controlled validation of the native discrete backbone.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15284 — 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 2026-10-15T23:54:14.752Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).