{
  "id": 725,
  "url": "https://arxiv.org/abs/2606.22724v1",
  "title": "Subspace-Constrained Federated Learning with Low-Rank Adaptation",
  "summary": "Federated low-rank adaptation methods are attractive for fine-tuning large models under communication and privacy constraints, but heterogeneous client data can induce geometric misalignment between local low-rank updates. We study whether this subspace misalignment leads to destructive aggregation and slower convergence in LoRA-based federated learning. We propose a subspace-regularized federated LoRA objective that encourages local client updates to remain close to a shared global reference su",
  "authors": "Neranjan Senarath, Rohit Muralitharan, Sadia Asif",
  "category": "research",
  "topics": "safety-alignment,privacy-surveillance",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-21T23:49:22.000Z",
  "fetched_at": "2026-07-14T14:14:46.033Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/725",
  "original_url": "https://arxiv.org/abs/2606.22724v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}