paper-with-me

Papers

Deep Domain Isolation and Sample Clustered Federated Learning for Semantic Segmentation

2024-10-04 · Matthis Manthe, Carole Lartizien, Stefan Duffner

Empirical studies show that federated learning exhibits convergence issues in Non Independent and Identically Distributed (IID) setups. However, these studies only focus on label distribution shifts, or concept shifts (e.g. ambiguous tasks). In this paper, we explore for the first time the effect of covariate shifts between participants' data in 2D segmentation tasks, showing an impact way less serious than label shifts but still present on convergence. Moreover, current Personalized (PFL) and Clustered (CFL) Federated Learning methods intrinsically assume the homogeneity of the dataset of each participant and its consistency with future test samples by operating at the client level. We introduce a more general and realistic framework where each participant owns a mixture of multiple underlying feature domain distributions. To diagnose such pathological feature distributions affecting a model being trained in a federated fashion, we develop Deep Domain Isolation (DDI) to isolate image domains directly in the gradient space of the model. A federated Gaussian Mixture Model is fit to the sample gradients of each class, while the results are combined with spectral clustering on the server side to isolate decentralized sample-level domains. We leverage this clustering algorithm through a Sample Clustered Federated Learning (SCFL) framework, performing standard federated learning of several independent models, one for each decentralized image domain. Finally, we train a classifier enabling to associate a test sample to its corresponding domain cluster at inference time, offering a final set of models that are agnostic to any assumptions on the test distribution of each participant. We validate our approach on a toy segmentation dataset as well as different partitionings of a combination of Cityscapes and GTA5 datasets using an EfficientVIT-B0 model, showing a significant performance gain compared to other approaches. Our code is available at https://github.com/MatthisManthe/DDI_SCFL .

📄 PDF Abstract BibTeX arXiv:2410.14693

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

NON 설명 없음
Spectral Clustering Spectral clustering has attracted increasing attention due to the promising ability in dealing with nonlinearly separable datasets [15], [16]. In spectral clustering, the…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

2022-10-05 · Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola 외

Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data. However, most of the exist…

Autonomous DrivingDomain AdaptationFederated LearningSemantic Segmentation+1

Stochastic Clustered Federated Learning

2023-03-02 · Dun Zeng, Xiangjing Hu, Shiyu Liu, Yue Yu 외

Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices. In real-world federated learning systems, these data samples are often decentralized and Non-…

Federated Learning

Analysis of Total Variation Minimization for Clustered Federated Learning

2024-03-10 · A. Jung

A key challenge in federated learning applications is the statistical heterogeneity of local datasets. Clustered federated learning addresses this challenge by identifying clusters of local datasets that are approximatel…

ClusteringFederated LearningGraph Learning

FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity

2024-04-14 · Yu Qiao, Huy Q. Le, Mengchun Zhang, Apurba Adhikary 외

Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge is that the distributed data is not ind…

ClusteringFederated LearningPrivacy Preserving

Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data

2024-12-18 · Junki Mori, Kosuke Kihara, Taiki Miyagawa, Akinori F. Ebihara 외

Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this problem, we focus on a source-free doma…

Domain AdaptationFederated LearningSemantic SegmentationSource-Free Domain Adaptation