paper-with-me

Papers

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning

2024-10-03 · Nurbek Tastan, Samuel Horvath, Martin Takac, Karthik Nandakumar

Statistical data heterogeneity is a significant barrier to convergence in federated learning (FL). While prior work has advanced heterogeneous FL through better optimization objectives, these methods fall short when there is extreme data heterogeneity among collaborating participants. We hypothesize that convergence under extreme data heterogeneity is primarily hindered due to the aggregation of conflicting updates from the participants in the initial collaboration rounds. To overcome this problem, we propose a warmup phase where each participant learns a personalized mask and updates only a subnetwork of the full model. This personalized warmup allows the participants to focus initially on learning specific subnetworks tailored to the heterogeneity of their data. After the warmup phase, the participants revert to standard federated optimization, where all parameters are communicated. We empirically demonstrate that the proposed personalized warmup via subnetworks (FedPeWS) approach improves accuracy and convergence speed over standard federated optimization methods.

📄 PDF Abstract BibTeX arXiv:2410.03042

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Focus 설명 없음

Similar Papers 제목 키워드 기반

FedSub: Introducing class-aware Subnetworks Fusion to Enhance Personalized Federated Learning in Ubiquitous Systems

2024-11-13 · Mattia Giovanni Campana, Franca Delmastro

Personalized Federated Learning is essential in AI-driven ubiquitous systems, supporting the distributed development of models able to adapt to diverse and evolving user behaviors while safeguarding privacy. Despite addr…

Activity RecognitionFederated LearningHuman Activity RecognitionPersonalized Federated Learning

GPSP: Graph Partition and Space Projection based Approach for Heterogeneous Network Embedding

2018-03-07 · Wenyu Du, Shuai Yu, Min Yang, Qiang Qu 외

In this paper, we propose GPSP, a novel Graph Partition and Space Projection based approach, to learn the representation of a heterogeneous network that consists of multiple types of nodes and links. Concretely, we first…

ClusteringGeneral ClassificationNetwork EmbeddingNode Classification

Hypernetworks for Model-Heterogeneous Personalized Federated Learning

2025-07-30 · Chen Zhang, Husheng Li, Xiang Liu, Linshan Jiang 외 arxiv

Recent advances in personalized federated learning have focused on addressing client model heterogeneity. However, most existing methods still require external data, rely on model decoupling, or adopt partial learning st…

Personalized Federated Learning

Let the Target Select for Itself: Data Selection via Target-Aligned Paths

2026-05-10 · Huitao Yang, Hengzhi He, Guang Cheng arxiv

Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many recent methods estimate candidate utility by aggregating local attributio…

On the adequacy of untuned warmup for adaptive optimization

2019-10-09 · Jerry Ma, Denis Yarats

Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Motivated by the difficulty of choosing and…

Image ClassificationLanguage ModellingMachine Translation