AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents

Yuqi Jia, Saeed Vahidian, Jingwei Sun, Jianyi Zhang, Vyacheslav Kungurtsev, Neil Zhenqiang Gong, Yiran Chen

ECCV 2024 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace aggregation-based FL (FedAvg) with server-side dataset distillation (FedDGM) under extreme heterogeneityFedDGM · CIFAR-10 (Dir 0.01, average)accuracy: 20.4 -> 63.4Improved
add generative-latent distillation on the server on top of FedDM-style distillationFedDM · CIFAR-10 (Dir 0.01, average)accuracy: 45.3 -> 63.4Improved
use FedDGM at near-iid partition (alpha 0.9) instead of FedDMFedDGM · CIFAR-10 (Dir 0.9, average)accuracy: 66.0 -> 67.5Improved
use FedDGM with a ViT global model at alpha 0.9 versus FedProxFedDGM · CIFAR-10 (Dir 0.9, ViT)accuracy: 55.0 -> 55.3No clear effect
use FedDGM on high-resolution ImageWoof with ResNet34 global modelFedDGM · ImageWoof (Dir 0.5, ResNet34)accuracy: 60.3 -> 72.7Improved
use FedDGM instead of FedDM on ImageFood (ResNet34)FedDGM · ImageFood (Dir 0.5, ResNet34)accuracy: 59.8 -> 60.0No clear effect
distill in F9 latent space instead of F5 (later layer) (ablation)FedDGM · CIFAR-10accuracyHurt
choose different StyleGAN-XL latent spaces among F0, F3, F4, F6 instead of F5 (ablation)FedDGM · CIFAR-10accuracyNo clear effect
increase images per class (IPC) from 1 to 20 (ablation)FedDGM · CIFAR-10accuracyImproved
use simpler (2-layer) local surrogate model (ablation)FedDM · CIFAR-10accuracyHurt
use simpler (2-layer) local surrogate model (ablation)FedDGM · CIFAR-10accuracyNo clear effect
vary local epochs away from 20 (more or fewer) (ablation)FedDGM · CIFAR-10accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy