HyperFedNet: Communication-Efficient Personalized Federated Learning Via Hypernetwork
The author proposes HyperFedNet (HFN) as an innovative approach to address challenges in Federated Learning by leveraging hypernetworks, reducing communication costs, and enhancing security.
Federated Learning with Global and Local Prompts Cooperation via Optimal Transport
The author presents Federated Prompts Cooperation via Optimal Transport (FedOTP) as a solution to address data heterogeneity in federated learning by integrating global and local prompts using unbalanced Optimal Transport. FedOTP effectively balances global consensus and local personalization, outperforming state-of-the-art methods.
FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
FedRDMA proposes a communication-efficient system integrating RDMA into federated learning, achieving up to 3.8× speedup in communication efficiency compared to traditional TCP/IP-based systems.
Enhancing Federated Generalization for Non-Participating Clients
The author advocates for improving federated learning's generalization by addressing the challenge of non-participating clients through innovative methods.
Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach
The author proposes a contribution-aware asynchronous Federated Learning method to address the challenges of slow and unreliable communication in realistic settings, offering a more efficient solution by dynamically adjusting update contributions based on staleness and statistical heterogeneity.
Adaptive Federated Learning Over the Air: Analysis and Performance Evaluation
The authors propose adaptive gradient methods within an over-the-air model training framework, enhancing robustness by adjusting step sizes dynamically. The convergence rates of AdaGrad and Adam-like algorithms are analyzed under various system factors.
Fairness-Aware Multi-Server Federated Learning Task Delegation over Wireless Networks
Optimizing task delegation in multi-server federated learning networks for fairness and efficiency.
FedUV: Emulating IID Setting for Federated Learning
FedUV promotes local models to emulate the IID setting, improving performance in non-IID scenarios.
FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models
Introducing FedComLoc, a novel approach integrating compression techniques into federated learning to reduce communication costs effectively.
Federated Learning with Global and Local Prompts Cooperation via Optimal Transport
FedOTP introduces efficient collaborative prompt learning strategies to address data heterogeneities in federated learning.
© 2024 by Linnk AI