{
  "abstract": "In high-dimensional tabular learning, feature screening provides a lightweight, model-agnostic way to remove irrelevant features before model fitting. However, scoring raw values directly can miss nonlinear or distributional structure. We introduce PACE (Plug-and-Play Contextual Embedding), which inserts a frozen tabular foundation model (TFM) column encoder before an existing feature-scoring rule, expanding each feature into a higher-dimensional contextual representation. Across controlled studies, PACE improves raw-space screening of complex nonlinear dependence with only modest additional encoding cost. These gains translate to downstream prediction on TALENT datasets: PACE-DC improves binary AUC by 0.077 and multiclass macro-AUC by 0.064, with a median normalized RMSE improvement of 0.063 across ten learners. Matched random-weight and random-feature controls show that PACE gains from pretrained structure beyond generic dimensional expansion. PACE further achieves favorable performance--time trade-offs against task-fitted selectors and attribution-based methods, positioning pretrained column geometry as a reusable upstream primitive for tabular learning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.23574",
  "author_total": 7,
  "authors": [
    {
      "name": "Qi Qin"
    },
    {
      "name": "Erbo Li"
    },
    {
      "name": "Ting Wei"
    },
    {
      "name": "Zizhou Huang"
    },
    {
      "name": "Zixuan Qin"
    },
    {
      "name": "Wu Wang"
    },
    {
      "name": "Yifan Sun"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/45xw8ykyzz441.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.23574",
  "fulltext_url": null,
  "id": "45xw8ykyzz441",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.23574",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning and Data Classification"
    ]
  ],
  "openalex": "W7214052264",
  "pdf_url": "https://arxiv.org/pdf/2609.23574",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/45xw8ykyzz441.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:33Z",
      "native_id": "2609.23574",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.23574"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models",
  "title_text": "PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:33Z",
  "url": "https://research.draconitic.com/paper/45xw8ykyzz441",
  "venue": "arXiv",
  "versions": []
}