AI Paper Atlas

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

FedL2P: Federated Learning to Personalize

Royson Lee, Minyoung Kim, Da Li, Xinchi Qiu, Timothy Hospedales, Ferenc Huszár, Nicholas Donald Lane

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Sparse and collaboration-graph personalization · 7 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
Use FedL2P's learned client-specific personalization strategy instead of fixed client BN fine-tuningCIFAR-10, FedAvg pretrained model, α=0.1, e=15 · CIFAR-10, α=0.1accuracy: 79.15±0.07 -> 80.28±0.07Improved
Use FedL2P's learned personalization strategy instead of client BN fine-tuningCIFAR-10-C, α=0.1 · CIFAR-10-C, α=0.1accuracy: 87.25±0.06 -> 89.23±0.15Improved
Use FedL2P's learned personalization strategy instead of incoming-batch BN statisticsOffice-Caltech-10, α=1000 · Office-Caltech-10, α=1000accuracy: 81.43±2.16 -> 88.85±0.89Improved
Use FedL2P instead of client BN fine-tuning on unseen speakersSpeech Commands, unseen clients, e=5 · Speech Commands, unseen clientsaccuracy: 62.76±1.83 -> 87.85±0.18Improved
Add LRNet to BNNet-only personalization (ablation)CIFAR-10, α=1000, e=15 · CIFAR-10, α=1000accuracy: 62.35±0.24 -> 65.13±0.02Improved
Add BNNet to LRNet with β fixed at 1 (ablation)CIFAR-10-C, α=1000, e=15 · CIFAR-10-C, α=1000accuracy: 60.09±0.02 -> 59.97±0.22No clear effect
Fix β at 0 instead of learning client BN mixing (ablation)DomainNet, α=1.0, e=15 · DomainNet, α=1.0accuracy: 63.77±0.44 -> divergeHurt
Replace IFT hypergradients with FOMAML+ (ablation)FedL2P on DomainNet, α=1000 · DomainNet, α=1000accuracy: 54.38±0.45 -> 52.70±0.17Hurt
Use local client HPO rather than federatedly learned meta-netsCIFAR-10, α=1000, e=15 · CIFAR-10, α=1000accuracy: 58.41±0.38 -> 65.13±0.02Hurt

Later papers that compared with this method

1 later accepted paper reports FedL2P 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