client heterogeneity 1federated learning 1low-rank adaptation 1model fine-tuning 1subspace allocation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning
Haobo Zhang, Jiankun Wang, Suraj Rajendran +5
The paper introduces Dysco, a plug‑in technique for federated fine‑tuning of large models that dynamically allocates client‑specific LoRA subspaces to reduce interference caused by…
cs.HC2025
TrialCompass: Visual Analytics for Enhancing the Eligibility Criteria Design of Clinical Trials
Rui Sheng, Xingbo Wang, Jiachen Wang +6
Eligibility criteria play a critical role in clinical trials by determining the target patient population, which significantly influences the outcomes of medical interventions. How…