{
  "id": 4289,
  "url": "https://arxiv.org/abs/2605.16446v2",
  "title": "Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating",
  "summary": "Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. We identify a structural conflict in tabular fair SSL through a diagnostic stress test: under confidence-gated pseudo-labeling, moment-matching fairness regularizers can trigger two failure modes -- Masking Collapse (fairness erodes confidence, starving pseudo-labels) and Trivial Saturation (drift to constant predictors",
  "authors": "Hangchuan Liang, Changchun Li",
  "category": "research",
  "topics": "bias-fairness,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-15T01:43:32.000Z",
  "fetched_at": "2026-07-14T16:30:54.919Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4289",
  "original_url": "https://arxiv.org/abs/2605.16446v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}