paper-with-me

Papers

FedCD: Improving Performance in non-IID Federated Learning

2020-06-17 · Kavya Kopparapu, Eric Lin, Jessica Zhao

Federated learning has been widely applied to enable decentralized devices, which each have their own local data, to learn a shared model. However, learning from real-world data can be challenging, as it is rarely identically and independently distributed (IID) across edge devices (a key assumption for current high-performing and low-bandwidth algorithms). We present a novel approach, FedCD, which clones and deletes models to dynamically group devices with similar data. Experiments on the CIFAR-10 dataset show that FedCD achieves higher accuracy and faster convergence compared to a FedAvg baseline on non-IID data while incurring minimal computation, communication, and storage overheads.

📄 PDF Abstract BibTeX arXiv:2006.09637

Code (2)

jessijzhao/fedcd 공식 구현
kavyakvk/FedCD

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Federated Causal Discovery From Interventions

2022-11-07 · Amin Abyaneh, Nino Scherrer, Patrick Schwab, Stefan Bauer 외

Causal discovery serves a pivotal role in mitigating model uncertainty through recovering the underlying causal mechanisms among variables. In many practical domains, such as healthcare, access to the data gathered by in…

Causal DiscoveryFederated LearningPrivacy Preserving

FedCD: A Fairness-aware Federated Cognitive Diagnosis Framework

2025-08-02 · Shangshang Yang, Jialin Han, Xiaoshan Yu, Ziwen Wang 외 arxiv

Online intelligent education platforms have generated a vast amount of distributed student learning data. This influx of data presents opportunities for cognitive diagnosis (CD) to assess students' mastery of knowledge c…

Federated Learning

FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling

2024-03-05 · Hongyu Zhang, Dongyi Zheng, Lin Zhong, Xu Yang 외

In recent years, Cross-Domain Recommendation (CDR) has drawn significant attention, which utilizes user data from multiple domains to enhance the recommendation performance. However, current CDR methods require sharing u…

Contrastive LearningData AugmentationFederated LearningGraph Learning+5

Federated Causal Discovery from Heterogeneous Data

2024-02-20 · Loka Li, Ignavier Ng, Gongxu Luo, Biwei Huang 외

Conventional causal discovery methods rely on centralized data, which is inconsistent with the decentralized nature of data in many real-world situations. This discrepancy has motivated the development of federated causa…

Causal Discovery

Reducing Spurious Correlation for Federated Domain Generalization

2024-07-27 · Shuran Ma, Weiying Xie, Daixun Li, Haowei Li 외

The rapid development of multimedia has provided a large amount of data with different distributions for visual tasks, forming different domains. Federated Learning (FL) can efficiently use this diverse data distributed …

Domain GeneralizationFederated Learningobject-detectionObject Detection