LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
Schema-aware split learning uses LLaMA-3.2-3B-Instruct as shared semantic encoder to harmonize heterogeneous mental-health surveys while raw data stays local.
The paper proposes a schema-aware split learning framework where an LLM serializes heterogeneous mental health survey records into natural language and is fine-tuned via LoRA, partitioned across client and server. Clients keep raw survey responses local and run only a lightweight front-end while the resource-intensive backbone runs server-side. Using LLaMA-3.2-3B-Instruct, the framework attains an average ANLS of 0.708 with 2,000 training samples, beats federated learning in eight of nine settings, and cuts per-client computation by three orders of magnitude while generalizing to unseen datasets.
- LLM semantic encoder unifies heterogeneous survey schemas across institutions
- Raw survey records never leave the collecting institution under split learning
- ANLS 0.708 with 2,000 samples; outperforms FL in eight of nine settings
- Per-client computation reduced by three orders of magnitude
From the original article
1 min read at arxiv.orgRising 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.
By Md Khalid Syfullah · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.