FedCD: Improving Performance in non-IID Federated Learning
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.
Code (2)
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Federated Causal Discovery From Interventions
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 PreservingFedCD: A Fairness-aware Federated Cognitive Diagnosis Framework
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 LearningFedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling
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+5Federated Causal Discovery from Heterogeneous Data
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 DiscoveryReducing Spurious Correlation for Federated Domain Generalization
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