Papers with Code 아카이브

Personalized Federated Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 7
보존된 평가 기록: 24

The federated learning setup presents numerous challenges including data heterogeneity (differences in data distribution), device heterogeneity (in terms of computation capabilities, network connection, etc.), and communication efficiency. Especially data heterogeneity makes it hard to learn a single shared global model that applies to all clients. To overcome these issues, Personalized Federated Learning (PFL) aims to personalize the global model for each client in the federation.

평가 결과

데이터셋과 평가 조건을 선택해 성능·논문·코드를 비교하세요. 보존된 Papers with Code 기록으로, 최신 순위는 아닙니다.

CIFAR-10

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 7건

CIFAR-100

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 7건

FEMNIST

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 2건

MNIST

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 2건

Omniglot

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 2건

Shakespeare

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 2건

Tiny ImageNet

원본 태스크: Federated Learning / Personalized Federated Learning

평가 기록 2건

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.