Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks

• URL: http://arxiv.org/abs/2312.13611v2
• Date: Mon, 11 Mar 2024 02:27:57 GMT
• Title: Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks
• Authors: Zheshun Wu, Zenglin Xu, Dun Zeng, Junfan Li, Jie Liu
• Abstract summary: Decentralized federated learning (DFL) has attracted significant interest in wireless device-to-device (D2D) networks. We conduct a theoretical convergence analysis for DFL and derive a convergence bound. We develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL.
• Score: 25.672506041978615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.

Related papers

• R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models [83.77114091471822]
  Split federated learning (SFL) is a compute-efficient paradigm in distributed machine learning (ML) A challenge in SFL, particularly when deployed over wireless channels, is the susceptibility of transmitted model parameters to adversarial jamming. This is particularly pronounced for word embedding parameters in large language models (LLMs), which are crucial for language understanding. A physical layer framework is developed for resilient SFL with LLMs (R-SFLLM) over wireless networks.
  arXiv  Detail & Related papers  (2024-07-16T12:21:29Z)
• Robust Decentralized Learning with Local Updates and Gradient Tracking [16.46727164965154]
  We consider decentralized learning as a network of communicating clients or nodes. We propose a decentralized minimax optimization method that employs two important data: local updates and gradient tracking.
  arXiv  Detail & Related papers  (2024-05-02T03:03:34Z)
• Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning [11.819765040106185]
  We propose an approach to create an optimal graph for data transfer using Reinforcement Learning. The goal is to form links that will provide the most benefit considering the environment's constraints. Numerical analysis shows the advantages in terms of convergence speed and straggler resilience of the proposed method.
  arXiv  Detail & Related papers  (2024-02-15T00:14:41Z)
• Over-the-Air Federated Learning and Optimization [52.5188988624998]
  We focus on Federated learning (FL) via edge-the-air computation (AirComp) We describe the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both convex and non- convex settings. For different types of local updates that can be transmitted by edge devices (i.e., model, gradient, model difference), we reveal that transmitting in AirFedAvg may cause an aggregation error. In addition, we consider more practical signal processing schemes to improve the communication efficiency and extend the convergence analysis to different forms of model aggregation error caused by these signal processing schemes.
  arXiv  Detail & Related papers  (2023-10-16T05:49:28Z)
• Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework [70.83511997272457]
  We propose a semi-federated learning (SemiFL) paradigm to leverage both the base station (BS) and devices for a hybrid implementation of centralized learning (CL) and FL. We propose a two-stage algorithm to solve this intractable problem, in which we provide the closed-form solutions to the beamformers.
  arXiv  Detail & Related papers  (2023-10-04T03:32:39Z)
• Analysis and Optimization of Wireless Federated Learning with Data Heterogeneity [72.85248553787538]
  This paper focuses on performance analysis and optimization for wireless FL, considering data heterogeneity, combined with wireless resource allocation. We formulate the loss function minimization problem, under constraints on long-term energy consumption and latency, and jointly optimize client scheduling, resource allocation, and the number of local training epochs (CRE) Experiments on real-world datasets demonstrate that the proposed algorithm outperforms other benchmarks in terms of the learning accuracy and energy consumption.
  arXiv  Detail & Related papers  (2023-08-04T04:18:01Z)
• SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks [56.68149211499535]
  Federated learning (FL) is a key enabler for efficient communication and computing leveraging devices' distributed computing capabilities. This paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNNs) We propose a communication and energy-efficient SNN-based FL (named SlimFL) that jointly utilizes superposition coding (SC) for global model aggregation and superposition training (ST) for updating local models.
  arXiv  Detail & Related papers  (2022-03-26T15:06:13Z)
• Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networks [50.68446003616802]
  Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices. We develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions. Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning.
  arXiv  Detail & Related papers  (2022-02-07T05:11:01Z)
• Spatio-Temporal Federated Learning for Massive Wireless Edge Networks [23.389249751372393]
  An edge server and numerous mobile devices (clients) jointly learn a global model without transporting huge amount of data collected by the mobile devices to the edge server. The proposed FL approach exploits spatial and temporal correlations between learning updates from different mobile devices scheduled to join STFL in various trainings. An analytical framework of STFL is proposed and employed to study the learning capability of STFL via its convergence performance.
  arXiv  Detail & Related papers  (2021-10-27T16:46:45Z)
• Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent [13.982904025739606]
  We propose a ring-topogy based decentralized federated learning scheme for Deep Generative Models (DGMs) Our RDFL schemes provides communication efficiency and maintain training performance to boost DGMs in target IIoT tasks. In addition, InterPlanetary File System(IPFS) is introduced to further improve communication efficiency and FL security.
  arXiv  Detail & Related papers  (2021-04-15T08:09:54Z)
• Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation [24.084053136210027]
  We develop a sampling methodology based on graph sequential convolutional networks (GCNs) We find that our methodology while sampling less than 5% of all devices outperforms conventional federated learning (FedL) substantially both in terms of trained model accuracy and required resource utilization.
  arXiv  Detail & Related papers  (2021-01-04T05:59:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.