AI Paper Atlas

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

Structured Federated Learning through Clustered Additive Modeling

Jie Ma, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 6 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 CAM to IFCAIFCA · CIFAR-10 cluster-wise Dirichlet, K=10accuracy: 34.84 -> 70.90Improved
add CAM to IFCAIFCA · Fashion-MNIST cluster-wise n-class (3,2), K=10macro-F1: 66.22 -> 82.98Improved
add CAM to FeSEMFeSEM · CIFAR-10 cluster-wise Dirichlet, K=10accuracy: 66.89 -> 78.45Improved
add CAM to FeSEMFeSEM · Fashion-MNIST cluster-wise n-class (3,2), K=10macro-F1: 84.43 -> 92.43Improved
add CAM to FeSEMFeSEM · CIFAR-10 client-wise Dirichlet 0.1, K=10macro-F1: 31.69 -> 59.19Improved
add CAM to IFCAIFCA · CIFAR-10 client-wise Dirichlet 0.1, K=10accuracy: 47.62 -> 72.54Improved
add CAM to IFCAIFCA · Fashion-MNIST client-wise n-class (2), K=5macro-F1: 72.30 -> 70.24No clear effect
ensemble FedAvg K=10 times (FedAvg+)FedAvg · Fashion-MNIST cluster-wise Dirichlet, K=10accuracy: 86.08 -> 89.42No clear effect
increase number of clusters K from 5 to 10 with CAMFeSEM-CAM · CIFAR-10 cluster-wise Dirichletaccuracy: 64.35 -> 78.45Improved
increase number of clusters K from 5 to 10 with CAMIFCA-CAM · CIFAR-10 cluster-wise Dirichletaccuracy: 58.13 -> 70.90Improved
increase K from 5 to 10 without CAMIFCA · Fashion-MNIST cluster-wise Dirichletaccuracy: 84.60 -> 82.10Hurt

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