AI Paper Atlas

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

Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing

Yongxin Guo, Lin Wang, Xiaoying Tang, Tao Lin

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 0 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
add Client2Vec (sampling+aggregation+local training, Federated index)FedAvg · CIFAR10accuracy: 42.24 -> 59.29Improved
add Client2Vec (all three case studies, Global index)FedDyn · CIFAR10accuracy: 37.22 -> 70.59Improved
add Client2Vec (all three case studies, Global index)FedAvg · DomainNetaccuracy: 46.31 -> 57.43Improved
add orthogonal loss to index generation (ablation)Client2Vec · CIFAR10accuracy: 15.32 -> 58.28Improved
add text align loss to index generation (ablation)Client2Vec · CIFAR10accuracy: 54.35 -> 58.28Improved
add reconstruction loss to index generation (ablation)Client2Vec · CIFAR10accuracy: 31.65 -> 58.28Improved
use DSA-IGN index instead of Feature Average index (ablation)Client2Vec · CIFAR10accuracy: 11.40 -> 58.28Improved
use DSA-IGN index instead of Class Prototypes index (ablation)Client2Vec · CIFAR10accuracy: 15.41 -> 58.28Improved
add label index to feature-only index (ablation)Client2Vec · CIFAR10accuracy: 44.99 -> 58.28Improved
add orthogonal regularization to local training (ablation)Client2Vec · CIFAR10accuracy: 43.71 -> 58.28Improved
add client-index-aware sampling only (Global, tau 1.0) (ablation)FedAvg · CIFAR10accuracy: 42.24 -> 45.56Improved
vary sampling temperature tau from 1.0 to 0.1 (Global index) (ablation)FedAvg · CIFAR10accuracy: 45.56 -> 41.28Hurt

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