AI Paper Atlas

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

Federated Learning from Pre-Trained Models: A Contrastive Learning Approach

Yue Tan, Guodong Long, Jie Ma, Lu Liu, Tianyi Zhou, Jing Jiang

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 65 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
Fuse multiple fixed pre-trained backbones and train with FedPCLLightweight federated learning · Digit-5, feature shift non-IID, averageaccuracy: 51.93(1.18) -> 55.34(0.34)Improved
Use both global and local prototypes for local contrastive training (ablation)FedPCL · Digit-5, feature shift non-IIDaccuracy: 54.69(0.14) -> 55.34(0.34)Improved
Use both global and local prototypes for local contrastive training (ablation)FedPCL · Digit-5, label shift non-IIDaccuracy: 44.75(1.77) -> 45.35(1.58)Improved
Use both global and local prototypes for local contrastive training (ablation)FedPCL · Digit-5, feature & label shift non-IIDaccuracy: 43.79(4.09) -> 45.22(3.65)Improved
Replace prototype-wise contrastive loss with cross-entropy (ablation)FedPCL · Digit-5, feature & label shift non-IIDaccuracy: 45.22(3.65) -> 32.98(3.44)Hurt
Replace prototype-wise contrastive loss with cross-entropy plus ProtoDist (ablation)FedPCL · Digit-5, feature & label shift non-IIDaccuracy: 45.22(3.65) -> 43.94(3.02)Hurt
Replace prototype-wise contrastive loss with supervised contrastive loss using local embeddings only (ablation)FedPCL · Digit-5, feature & label shift non-IIDaccuracy: 45.22(3.65) -> 42.18(3.25)Hurt
Increase the number of fixed backbones from 1 to 3 (ablation)FedPCL · Digit-5, feature & label shift non-IIDaccuracy: 42.87(1.47) -> 45.22(3.65)Improved
Increase the number of fixed backbones from 2 to 3 (ablation)FedPCL · Digit-5, feature & label shift non-IIDaccuracy: 44.49(1.75) -> 45.22(3.65)Improved
Add noise to communicated prototypes (ablation)FedPCL · Office-10, label shift non-IIDaccuracy: 42.13(0.77) -> 39.93(3.48) (Laplace, p=0.1); 42.13(0.77) -> 40.04(2.09) (Gaussian, p=0.1)Hurt
Use three fixed backbones instead of one (ablation)Lightweight federated learning · Digit-5, feature shift non-IID, FedPCLaccuracy: 52.83(0.21) -> 55.34(0.34)Improved

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