FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models
cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/EnsiehKhazaei/FedLoVA
Terminology
Sources
- Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models
- Training Verifiers to Solve Math Word Problems
- Harmonizing Generalization and Personalization in Federated Prompt Learning
- Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
- Latent Information Sharing for Accelerating Federated Learning
- Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision
- On the Convergence of FedAvg on Non-IID Data
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning
- FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
- LLaMA: Open and Efficient Foundation Language Models
- Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis