paper-with-me

홈 › Papers

FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing

2025-05-13 · Haodong Zhao, Peng Peng, Chiyu Chen, Linqing Huang, Gongshen Liu

Remote sensing (RS) images are usually produced at an unprecedented scale, yet they are geographically and institutionally distributed, making centralized model training challenging due to data-sharing restrictions and privacy concerns. Federated learning (FL) offers a solution by enabling collaborative model training across decentralized RS data sources without exposing raw data. However, there lacks a realistic federated dataset and benchmark in RS. Prior works typically rely on manually partitioned single dataset, which fail to capture the heterogeneity and scale of real-world RS data, and often use inconsistent experimental setups, hindering fair comparison. To address this gap, we propose a realistic federated RS dataset, termed FedRS. FedRS consists of eight datasets that cover various sensors and resolutions and builds 135 clients, which is representative of realistic operational scenarios. Data for each client come from the same source, exhibiting authentic federated properties such as skewed label distributions, imbalanced client data volumes, and domain heterogeneity across clients. These characteristics reflect practical challenges in federated RS and support evaluation of FL methods at scale. Based on FedRS, we implement 10 baseline FL algorithms and evaluation metrics to construct the comprehensive FedRS-Bench. The experimental results demonstrate that FL can consistently improve model performance over training on isolated data silos, while revealing performance trade-offs of different methods under varying client heterogeneity and availability conditions. We hope FedRS-Bench will accelerate research on large-scale, realistic FL in RS by providing a standardized, rich testbed and facilitating fair comparisons across future works. The source codes and dataset are available at https://fedrs-bench.github.io/.

📄 PDF Abstract BibTeX arXiv:2505.08325

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units

2024-01-23 · Shaoheng Fang, Rui Ye, Wenhao Wang, Zuhong Liu 외

Roadside unit (RSU) can significantly improve the safety and robustness of autonomous vehicles through Vehicle-to-Everything (V2X) communication. Currently, the usage of a single RSU mainly focuses on real-time inference…

Autonomous VehiclesFederated LearningScene Flow EstimationSelf-Supervised Learning+1

FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Models

2025-01-05 · Hui Lin, Chao Zhang, Danfeng Hong, Kexin Dong 외

Remote sensing data is often distributed across multiple institutions, and due to privacy concerns and data-sharing restrictions, leveraging large-scale datasets in a centralized training framework is challenging. Federa…

Federated Learningimage-classificationImage ClassificationPrompt Learning+3

Efficient and Robust Regularized Federated Recommendation

2024-11-03 · Langming Liu, Wanyu Wang, Xiangyu Zhao, Zijian Zhang 외

Recommender systems play a pivotal role across practical scenarios, showcasing remarkable capabilities in user preference modeling. However, the centralized learning paradigm predominantly used raises serious privacy con…

Federated LearningRecommendation Systems

FedCME: Client Matching and Classifier Exchanging to Handle Data Heterogeneity in Federated Learning

2023-07-17 · Jun Nie, Danyang Xiao, Lei Yang, Weigang Wu

Data heterogeneity across clients is one of the key challenges in Federated Learning (FL), which may slow down the global model convergence and even weaken global model performance. Most existing approaches tackle the he…

Federated Learning

Benchmarking Algorithms for Federated Domain Generalization

2023-07-11 · Ruqi Bai, Saurabh Bagchi, David I. Inouye

While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges. Additionally, we explore domain-based he…

BenchmarkingDiversityDomain GeneralizationFederated Learning