Communication-Efficient Zero-Order and First-Order Federated Learning Methods Over Wireless Networks
1mo ago
Source
IEEECommunication-Efficient Zero-Order and First-Order Federated Learning Methods Over Wireless Networksieee.orgFederated Learning (FL) is an emerging learning framework that enables edge devices to collaboratively train ML models without sharing their local data. However, FL faces a significant challenge due to the high amount of information that must be exchanged between devices and the aggregator in the training phase, which can exceed the limited capacity of wireless systems. In this paper, two communication-efficient FL methods are considered, where communication overhead is reduced by communicating scalar values instead of long vectors and by allowing a high number of users to send information simultaneously. The first approach employs a zero-order optimization technique with a two-point gradient estimator, while the second involves a first-order gradient computation strategy. The novelty lies in leveraging channel information in the learning algorithms, hence eliminating the need for additional resources to acquire channel state information (CSI) and to remove its impact, as well as in considering asynchronous devices. We provide a rigorous analytical framework for the two methods, deriving convergence guarantees and establishing appropriate performance bounds.
You might also wanna read
FedHENet: A Federated Learning Framework Using Homomorphic Encryption for Efficient Image Classification
This paper introduces FedHENet, a federated learning framework for image classification that extends the FedHEONN approach. It uses a fixed
arxiv.org·1mo ago
Fast-dLLM: Training-Free Acceleration Method for Diffusion Language Models Using KV Cache and Parallel Decoding
Researchers introduce Fast-dLLM, a training-free acceleration method for diffusion-based large language models that addresses their slower i
arxiv.org·8mo ago
Differentially private federated learning for localized control of infectious disease dynamics
nature.com·1d ago
Distributed Quantum Learning: Convergence Analysis and Adaptive Post-Quantum Security Framework
This paper presents a comprehensive study on Distributed Quantum Learning (DQL), focusing on two key aspects: convergence analysis under pra
arxiv.org·15d ago
Rank-Aware Decomposition Technique Reduces Computation in Recommender Systems by 87.5%
This paper presents a rank-aware decomposition technique for deep ranking models in industrial recommender systems. The key insight is that
arxiv.org·1mo ago
LK Losses: A New Training Objective to Optimize Acceptance Rate in Speculative Decoding for LLMs
This paper introduces LK losses, a novel training objective for speculative decoding in large language models (LLMs). Speculative decoding a
arxiv.org·1mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.