paper-with-me

홈 › Papers

Prioritizing Gradient Sign Over Modulus: An Importance-Aware Framework for Wireless Federated Learning

2026-03-11 · Yiyang Yue, Jiacheng Yao, Wei Xu, Zhaohui Yang, George K. Karagiannidis, Dusit Niyato arxiv

Wireless federated learning (FL) facilitates collaborative training of artificial intelligence (AI) models to support ubiquitous intelligent applications at the wireless edge. However, the inherent constraints of limited wireless resources inevitably lead to unreliable communication, which poses a significant challenge to wireless FL. To overcome this challenge, we propose Sign-Prioritized FL (SP-FL), a novel framework that improves wireless FL by prioritizing the transmission of important gradient information through uneven resource allocation. Specifically, recognizing the importance of descent direction in model updating, we transmit gradient signs in individual packets and allow their reuse for gradient descent if the remaining gradient modulus cannot be correctly recovered. To further improve the reliability of transmission of important information, we formulate a hierarchical resource allocation problem based on the importance disparity at both the packet and device levels, optimizing bandwidth allocation across multiple devices and power allocation between sign and modulus packets. To make the problem tractable, the one-step convergence behavior of SP-FL, which characterizes data importance at both levels in an explicit form, is analyzed. We then propose an alternating optimization algorithm to solve this problem using the Newton-Raphson method and successive convex approximation (SCA). Simulation results confirm the superiority of SP-FL, especially in resource-constrained scenarios, demonstrating up to 9.96\% higher testing accuracy on the CIFAR-10 dataset compared to existing methods.

📄 PDF Abstract BibTeX arXiv:2603.10763

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Training Deep Models Faster with Robust, Approximate Importance Sampling

2018-12-01 · NeurIPS 2018 12 · Tyler B. Johnson, Carlos Guestrin

In theory, importance sampling speeds up stochastic gradient algorithms for supervised learning by prioritizing training examples. In practice, the cost of computing importances greatly limits the impact of importance sa…

Compressed Sensing Constant Modulus Constrained Projection Matrix Design and High-Resolution DoA Estimation Methods

2021-10-07 · Khaled Ardah, Martin Haardt

This paper proposes a compressed sensing-based high-resolution direction-of-arrival estimation method called gradient orthogonal matching pursuit (GOMP). It contains two main steps: a sparse coding approximation step usi…

compressed sensingDirection of Arrival Estimation

Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay

2021-11-02 · Dogan C. Cicek, Enes Duran, Baturay Saglam, Furkan B. Mutlu 외

The experience replay mechanism allows agents to use the experiences multiple times. In prior works, the sampling probability of the transitions was adjusted according to their importance. Reassigning sampling probabilit…

Computational Efficiencycontinuous-controlContinuous Control

Empirical study of the modulus as activation function in computer vision applications

2023-01-15 · Iván Vallés-Pérez, Emilio Soria-Olivas, Marcelino Martínez-Sober, Antonio J. Serrano-López 외

In this work we propose a new non-monotonic activation function: the modulus. The majority of the reported research on nonlinearities is focused on monotonic functions. We empirically demonstrate how by using the modulus…

Extreme Point Pursuit -- Part I: A Framework for Constant Modulus Optimization

2024-03-11 · Junbin Liu, Ya Liu, Wing-Kin Ma, Mingjie Shao 외

This study develops a framework for a class of constant modulus (CM) optimization problems, which covers binary constraints, discrete phase constraints, semi-orthogonal matrix constraints, non-negative semi-orthogonal ma…