AI Paper Atlas

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

SphereFed: Hyperspherical Federated Learning

Xin Dong, Sai Qian Zhang, Ang Li, H.T. Kung

ECCV 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 24 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 SphereFed (fixed classifier, feature norm, MSE, FFC) to FedAvgFedAvg MobileNetV2 · CIFAR-100 (alpha=0.1)accuracy (%): 63.90 -> 66.52 (up 2.62)Improved
add SphereFed to FedNovaFedNova VGG13 · TinyImageNetaccuracy (%): 39.63 -> 45.21 (up 5.58)Improved
add SphereFed to FedOptFedOpt SENet · CIFAR-100 (alpha=0.5)accuracy (%): 59.60 -> 65.69 (up 6.09)Improved
add CCVR to FedAvgFedAvg MobileNetV2 · CIFAR-100 (alpha=0.5)accuracy (%): 68.78 -> 69.14 (up 0.36)Improved
add BABU to FedAvgFedAvg MobileNetV2 · TinyImageNetaccuracy (%): 29.95 -> 28.38 (down 1.57)Hurt
add fixed random classifier (ablation)FedAvg MobileNetV2 with CE · CIFAR-100 (alpha=0.5)accuracy (%): 68.78 -> 69.35 (up 0.57)Improved
fix classifier with orthogonal unit-norm init instead of random (ablation)FedAvg MobileNetV2 with CE · CIFAR-100 (alpha=0.5)accuracy (%): 69.35 -> 69.65Improved
add feature normalization to Fix (OU) (ablation)FedAvg MobileNetV2 with CE · CIFAR-100 (alpha=0.5)accuracy (%): 69.65 -> 70.87Improved
replace CE with MSE loss on the full hyperspherical setup (ablation)FedAvg + Fix (OU) + Norm · CIFAR-100 (alpha=0.5)accuracy (%): 70.87 -> 71.85Improved
add feature normalization alone with MSE loss (no fixed classifier) (ablation)FedAvg MobileNetV2 with MSE · CIFAR-100 (alpha=0.5)accuracy (%): 66.42 -> DivergingHurt
replace CE with MSE without fixed classifier or norm (ablation)FedAvg MobileNetV2 · CIFAR-100 (alpha=0.5)accuracy (%): 68.78 -> 66.42Hurt
add l2 penalty on calibrated classifier weights in FFC (ablation)SphereFed FFC · CIFAR-100 (alpha=0.5)accuracy (%): 71.85 -> 71.96No clear effect

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