Hierarchical Optimization Method for Federated Learning with Feature Alignment and Decision Fusion
Source abstract
Abstract
In the realm of data privacy protection, federated learning aims to collaboratively train a global model. However, heterogeneous data between clients presents challenges, often resulting in slow convergence and inadequate acc... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (36)
Show source-provided references
1. Evolutionary privacy-preserving learning strategies for edge-based IoT data sharing schemes10.1016/j.dcan.2022.05.004 ↗
2. Deep learning10.1038/nature14539 ↗
3. Privacy-preserving offloading scheme in multi-access mobile edge computing based on MADRL10.1016/j.jpdc.2023.104775 ↗
4. Combining Lyapunov optimization with actor-critic networks for privacy-aware IIoT computation offloading10.1109/JIOT.2024.3357110 ↗
5. Emerging trends in federated learning: From model fusion to federated x learning10.1007/s13042-024-02119-1 ↗
6. FedTwin: Blockchain-enabled adaptive asynchronous federated learning for digital twin networks10.1109/MNET.105.2100620 ↗
7. Communication-efficient learning of deep networks from decentralized data
8. Preserving data privacy via federated learning: Challenges and solutions10.1109/MCE.2019.2959108 ↗
9. Federated learning on non-IID data silos: An experimental study
10. Personalized federated learning for intelligent IoT applications: A cloud-edge based framework10.1109/OJCS.2020.2993259 ↗
11. Advances and open problems in federated learning10.1561/2200000083 ↗
12. Representation learning: A review and new perspectives10.1109/TPAMI.2013.50 ↗
13. Exploiting shared representations for personalized federated learning
14. Federated optimization in heterogeneous networks
15. SCAFFOLD: Stochastic controlled averaging for federated learning
16. Y. Zhao et al., “Federated learning with non-IID data,” 2018, arXiv:1806.00582.
17. Clustered sampling: Low-variance and improved representativity for clients selection in federated learning
18. Meta-learning in neural networks: A survey
19. Model-agnostic meta-learning for fast adaptation of deep networks
20. Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach
21. Personalized cross-silo federated learning on non-IID data
22. Federated multi-task learning under a mixture of distributions
23. FedProto: Federated prototype learning across heterogeneous clients
24. GPFL: Simultaneously learning global and personalized feature information for personalized federated learning
25. LightFed: An efficient and secure federated edge learning system on model splitting
26. Federated feature concatenate method for heterogeneous computing in federated learning
27. FedTC: A personalized federated learning method with two classifiers
28. FedGH: Heterogeneous federated learning with generalized global header
29. Prototypical networks for few-shot learning
30. J. N. Li, P. Zhou, C. Xiong, and S. C. H. Hoi, “Prototypical contrastive learning of unsupervised representations,” 2020, arXiv:2005.04966.
31. A review: Deep learning for medical image segmentation using multi-modality fusion
32. One-dimensional VGGNet for high-dimensional data10.1016/j.asoc.2023.110035 ↗
33. H. Xiao, K. Rasul, and R. Vollgraf, “Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms,” 2017, arXiv:1708.07747.
34. A. Krizhevsky and G. Hinton, “Learning multiple layers of features from tiny images,” in Handbook of Systemic Autoimmune, 2009.
35. Deep cosine metric learning for person re-identification
36. Deep residual learning for image recognition