Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleDecember 2024
ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issues
ACM MobiCom '24: Proceedings of the 30th Annual International Conference on Mobile Computing and NetworkingPages 845–860https://doi.org/10.1145/3636534.3690665Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS) and accelerate ...
- research-articleFebruary 2024
Addressing Heterogeneity in Federated Learning with Client Selection via Submodular Optimization
ACM Transactions on Sensor Networks (TOSN), Volume 20, Issue 2Article No.: 48, Pages 1–32https://doi.org/10.1145/3638052Federated learning (FL) has been proposed as a privacy-preserving distributed learning paradigm, which differs from traditional distributed learning in two main aspects: the systems heterogeneity, meaning that clients participating in training have ...
- research-articleAugust 2023
FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 3249–3261https://doi.org/10.1145/3580305.3599345Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL methods ...
- research-articleAugust 2023
FedAPEN: Personalized Cross-silo Federated Learning with Adaptability to Statistical Heterogeneity
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1954–1964https://doi.org/10.1145/3580305.3599344In cross-silo federated learning (FL), the data among clients are usually statistically heterogeneous (aka not independent and identically distributed, non-IID) due to diversified data sources, lowering the accuracy of FL. Although many personalized FL (...
- ArticleMay 2023
pFedV: Mitigating Feature Distribution Skewness via Personalized Federated Learning with Variational Distribution Constraints
Advances in Knowledge Discovery and Data MiningPages 283–294https://doi.org/10.1007/978-3-031-33377-4_22AbstractStatistical heterogeneity, especially feature distribution skewness, among the distributed data is a common phenomenon in practice, which is a challenging problem in federated learning that can lead to a degradation in the performance of the ...
