FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning
cs.LG, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Git Re-Basin: Merging Models modulo Permutation Symmetries
- Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networks
- Fusing finetuned models for better pretraining
- CINIC-10 is not ImageNet or CIFAR-10
- The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
- One-Shot Federated Learning
- Editing Models with Task Arithmetic
- Dataless Knowledge Fusion by Merging Weights of Language Models
- Practical One-Shot Federated Learning for Cross-Silo Setting
- FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
- Federated Learning with Matched Averaging
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