TsingZ0/FedKTL
CVPR 2024 accepted paper, An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
This project helps machine learning researchers improve the performance of many small, diverse AI models, like those on individual devices, by leveraging a powerful centralized image generator. It takes a pre-trained image generator (like Stable Diffusion) and various client datasets as input, and outputs small, personalized models that perform better on their specific tasks. This is ideal for AI researchers working with distributed model training and privacy-sensitive data.
No commits in the last 6 months.
Use this if you are a machine learning researcher focused on federated learning and need to enhance the capabilities of many client-side AI models with limited data, while efficiently utilizing a powerful pre-trained generative model.
Not ideal if you are looking for a plug-and-play solution for general image generation or if your primary concern is not federated learning with heterogeneous models.
Stars
66
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TsingZ0/FedKTL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...