AI Paper Atlas

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

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

Zikai Xiao, Zihan Chen, Songshang Liu, Hualiang Wang, YANG FENG, Jin Hao, Joey Tianyi Zhou, Jian Wu, Howard Hao Yang, Zuozhu Liu

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 4 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 Fed-GraB (DPA + SGB) to FedAvgFedAvg · CIFAR-10-LT alpha=1, IF_G=100overall accuracy: 0.737 -> 0.766Improved
Add Fed-GraB to FedAvgFedAvg · CIFAR-10-LT alpha=0.5, IF_G=100overall accuracy: 0.719 -> 0.761Improved
Add Fed-GraB to FedAvgFedAvg · CIFAR-100-LToverall accuracy: 0.365 -> 0.411Improved
Add Fed-GraB to FedAvgFedAvg · ImageNet-LToverall accuracy: 0.287 -> 0.311Improved
Add Fed-GraB to FedAvgFedAvg · iNaturalist-160koverall accuracy: 0.434 -> 0.451Improved
Apply SGB in centralized learning vs SoftmaxSoftmax · CIFAR-10-LT centralized, IF=100overall accuracy: 0.767 -> 0.818Improved
Use Fed-GraB instead of FedAvg for tail-class communication efficiencyFedAvg · CIFAR-10-LT IF_G=50 alpha=1rounds to 55% tail accuracy: 96 -> 59Improved
Use Fed-GraB instead of FedAvg for tail-class communication efficiencyFedAvg · CIFAR-10-LT IF_G=100 alpha=0.5rounds to 55% tail accuracy: 192 -> 122Improved
Use Fed-GraB instead of Eqlv2-FL, which cannot align Delta(t)Eqlv2-FL · CIFAR-10-LT IF_G=50 alpha=1rounds to 55% tail accuracy: 301 -> 59Improved
Use global prior vector from DPA instead of local distribution (Local-SGB) (ablation)SGB · CIFAR-10-LTtest accuracyImproved
Mount SGB on all classes with DPA instead of only tail classes 7 to 9 (ablation)SGB · CIFAR-10-LTtest accuracyImproved
Use proportional gain K_P=10 versus K_P=1 (ablation)SGB controller · CIFAR-10-LTDelta(t) controlImproved

Later papers that compared with this method

1 later accepted paper reports Fed-Grab as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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