deep learning · federated learning · efficient adaptation
Federated Vision Transformers
A collaborative research codebase comparing centralized and federated Vision Transformer training on CIFAR-100 with DINO backbones, LoRA and TaLoS-style model editing.
Problem
Federated visual learning combines non-IID data, distributed optimization and constrained client resources. The project explores whether parameter-efficient fine-tuning and model-editing strategies can be evaluated in a shared centralized/federated codebase.
What I built
The repository includes centralized and federated training scripts, a simulated client/server core, ViT models with DINO-pretrained backbones, LoRA and TaLoS-style editing modules, YAML configuration and Weights & Biases experiment tracking.
The same codebase supports centralized and client-server experiments with multiple fine-tuning strategies.
Engineering decisions
Where the project becomes more than a demo.
The details that matter are usually in the constraints: who is allowed to decide, what gets measured, what is kept separate, and how failure is represented.
Keep centralized and federated paths comparable.
Shared model and configuration surfaces reduce the number of moving parts when comparing training modes.
Make adaptation strategy configurable.
Dense, LoRA and pruning/editing strategies can be switched through configuration rather than forked experiments.
Treat heterogeneity as part of the setup.
The client-server simulation is designed around non-IID client data and distributed aggregation instead of an IID toy assumption.
Evidence
What the repository actually supports.
dense, LoRA and TaLoS-style editing
DINO-pretrained Vision Transformer features
sweeps and experiment logging integrated into the workflow
Limits
What I am not claiming.
- This is collaborative academic research, not a production federated-learning platform.
- The repository README does not support a single headline performance number, so the site does not invent one.
- The work is presented with explicit collaborative attribution.
Signal