Balancing Data Privacy and Efficiency in Federated Learning with Social Connections
The author argues that by leveraging social connections, a novel Social-aware Clustered Federated Learning scheme can enhance model utility without sacrificing privacy. This approach strikes a balance between data privacy and efficiency in federated learning.
Federated Learning Using Coupled Tensor Train Decomposition: Privacy-Preserving Distributed Machine Learning
The author proposes a coupled tensor train decomposition approach for privacy-preserving federated learning, achieving data confidentiality and computational efficiency.
Achieving Near-optimal Utility for Privacy-Preserving Federated Learning
The authors aim to achieve near-optimal utility in privacy-preserving federated learning through data generation and parameter distortion.
Federated Learning Using Coupled Tensor Train Decomposition: Privacy-Preserving Distributed Machine Learning Technique
Proposing a novel approach, Coupled Tensor Train Decomposition (CTT), for privacy-preserving federated learning networks.
ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations
ALI-DPFL algorithm improves performance in resource-constrained scenarios through adaptive local iterations.
Auditable Homomorphic-based Decentralized Collaborative AI with Attribute-based Differential Privacy
Proposing AerisAI for secure decentralized AI collaboration with differential privacy and homomorphic encryption.
Federated Learning: Balancing Privacy and Accuracy
Collaborative federated learning protocols must balance privacy guarantees and model accuracy to be mutually beneficial for all participants.
Preserving Privacy in Federated Learning through Differential Privacy
Federated learning and differential privacy can be combined to enable large-scale machine learning over distributed datasets while providing rigorous privacy guarantees.
© 2024 by Linnk AI