Metraipolis › archive › dc_c6399508fb30

LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys — arXiv:2609.15871

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15871
License (as archived)
CC0-1.0
Archived
2026-10-15T22:54:08.102Z
SHA-256 of the archived text
fb9474a1a1a03c956a33024e361e6f0cfed502b92285a487f57448f435ad48ad
Stable URL of this page
https://metraipolis.com/documento/dc_c6399508fb30

How to cite

LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys — arXiv:2609.15871 — arXiv (en), https://arxiv.org/abs/2609.15871 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c6399508fb30 (Metraipolis archive dc_c6399508fb30, sha256 fb9474a1a1a03c956a33024e361e6f0cfed502b92285a487f57448f435ad48ad)
BibTeX
@misc{dcc6399508fb30,
  title = {LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys — arXiv:2609.15871},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15871},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c6399508fb30; sha256 fb9474a1a1a03c956a33024e361e6f0cfed502b92285a487f57448f435ad48ad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15871. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rising societal and lifestyle complexity has been linked to a growing prevalence of mental distress worldwide. Educational institutions, workplaces, clinics, etc. collect large volumes of mental health survey data to understand and reduce this burden. Collaborative analysis of such data could yield effective generalizable predictive models. Privacy constraints and varied survey designs (i.e., different questions, scales, and formats) hinder direct integration. We propose a schema-aware split learning (SL) framework that preserves privacy, using a large language model (LLM) as a shared semantic encoder to harmonize heterogeneous survey schemas across institutions. We serialize each survey record into a natural-language description, unifying disparate survey schemas into a common format. The LLM is fine-tuned for mental distress assessment via Low-Rank Adaptation (LoRA) and partitioned across client and server. Clients retain the raw survey responses locally and run only a lightweight front-end, so original records never leave the institution that collected them. The resource-intensive backbone runs on the server, minimizing client-side computation. Using LLaMA-3.2-3B-Instruct, the framework attains an average ANLS of 0.708 with only 2,000 training samples, surpasses federated learning (FL) in eight of nine settings, and cuts per-client computation by three orders of magnitude, while generalizing to unseen datasets. Overall, it enables accurate, privacy-preserving, and resource-efficient collaborative learning from heterogeneous mental health survey data.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.15871 — 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 2026-10-15T22:29:03.941Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).