AI Paper Atlas

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

Eliminating Domain Bias for Federated Learning in Representation Space

Jianqing Zhang, Yang Hua, Jian Cao, Hao Wang, Tao Song, Zhengui XUE, Ruhui Ma, Haibing Guan

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 11 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 mean regularization (MR) alone (ablation)FedAvg · Tiny-ImageNet 4-layer CNNaccuracy: 19.46 -> 22.21Improved
add personalized representation bias memory (PRBM) alone (ablation)FedAvg · Tiny-ImageNet 4-layer CNNaccuracy: 19.46 -> 26.70Improved
add both PRBM and MR (full DBE) (ablation)FedAvg · Tiny-ImageNet 4-layer CNNaccuracy: 19.46 -> 43.32Improved
add MR alone (ablation)FedAvg · Tiny-ImageNet 4-layer CNNMDL (bits): 3844 -> 3643Improved
add PRBM alone (ablation)FedAvg · Tiny-ImageNet ResNet-18accuracy: 19.45 -> 38.27Improved
add MR alone (ablation)FedAvg · Tiny-ImageNet ResNet-18accuracy: 19.45 -> 20.85Improved
insert DBE after CONV2 instead of after FC1 (ablation)FedAvg+DBE · Tiny-ImageNet 4-layer CNNaccuracy: 43.32 -> 47.03Improved
insert DBE after CONV1 instead of after FC1 (ablation)FedAvg+DBE · Tiny-ImageNet 4-layer CNNaccuracy: 43.32 -> 21.81Hurt
add DBE to SCAFFOLDSCAFFOLD · Cifar100accuracy: 33.08 -> 63.61Improved
add DBE to FedGenFedGen · AG Newsaccuracy: 89.86 -> 97.16Improved
add Gaussian noise (s=5, q=0.2) to client means (ablation)FedAvg+DBE · Tiny-ImageNetaccuracy: 43.32 -> 36.27Hurt
add small Gaussian noise (s=0.05, q=0.2) to client means (ablation)FedAvg+DBE · Tiny-ImageNetaccuracy: 43.32 -> 44.10No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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