NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection

• URL: http://arxiv.org/abs/2411.13000v1
• Date: Wed, 20 Nov 2024 02:53:04 GMT
• Title: NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection
• Abstract summary: Over-the-air federated learning (FL), i.e., AirFL, leverages computing primitively over multiple access channels. A long-standing challenge in AirFL is to achieve coherent signal alignment without relying on expensive channel estimation and feedback.
• Score: 36.492934314653766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over-the-air federated learning (FL), i.e., AirFL, leverages computing primitively over multiple access channels. A long-standing challenge in AirFL is to achieve coherent signal alignment without relying on expensive channel estimation and feedback. This paper proposes NCAirFL, a CSI-free AirFL scheme based on unbiased non-coherent detection at the edge server. By exploiting binary dithering and a long-term memory based error-compensation mechanism, NCAirFL achieves a convergence rate of order $\mathcal{O}(1/\sqrt{T})$ in terms of the average square norm of the gradient for general non-convex and smooth objectives, where $T$ is the number of communication rounds. Experiments demonstrate the competitive performance of NCAirFL compared to vanilla FL with ideal communications and to coherent transmission-based benchmarks.

Related papers

• Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling [32.15907297197385]
  Non-coherent AirFL protocol over a single-antenna MAC.<n>Non-coherent AirFL protocol over a single-antenna MAC, leveraging binary dithering, unbiased non-coherent error feedback.
  arXiv  Detail & Related papers  (2026-09-08T06:34:13Z)
• On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients [2.2530496464901106]
  The holy grail of machine learning is to enable Continual Federated Learning (CFL) to enhance the efficiency, privacy, and scalability of AI systems while learning from streaming data. We propose a novel replay-memory based federated strategy consisting of edge-based gradient updates on memory and aggregated gradients on the current data. We empirically show that C-FLAG outperforms several state-of-the-art baselines on both task and class-incremental settings with respect to metrics such as accuracy and forgetting.
  arXiv  Detail & Related papers  (2024-11-12T17:36:20Z)
• UAV-assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis [16.963596661873954]
  Hierarchical federated learning (HFL) is a key paradigm to distribute learning across edge devices to reach global intelligence. In HFL, each edge device trains a local model using its respective data and transmits the updated model parameters to an edge server for local aggregation. This paper proposes an unbiased HFL algorithm for unmanned aerial vehicle (UAV)-assisted wireless networks.
  arXiv  Detail & Related papers  (2024-07-05T06:23:01Z)
• Communication-efficient Vertical Federated Learning via Compressed Error Feedback [24.32409923443071]
  Communication overhead is a known bottleneck in learning (FL) We propose error feedback over federated networks to train networks. EFVFL does not require a vanishing compression error for smooth non-significant problems.
  arXiv  Detail & Related papers  (2024-06-20T15:40:38Z)
• Sharp Bounds for Sequential Federated Learning on Heterogeneous Data [5.872735527071425]
  In Federated Learning (FL), models are trained in a parallel manner across clients, and in sequential FL (SFL) models are trained in a sequential manner across clients. In contrast to PFL, convergence theory of SFL data is still lacking. We establish sharp convergence guarantees for SFL on heterogeneous data with both upper and lower bounds.
  arXiv  Detail & Related papers  (2024-05-02T09:58:49Z)
• Hierarchical Personalized Federated Learning Over Massive Mobile Edge Computing Networks [95.39148209543175]
  We propose hierarchical PFL (HPFL), an algorithm for deploying PFL over massive MEC networks. HPFL combines the objectives of training loss minimization and round latency minimization while jointly determining the optimal bandwidth allocation.
  arXiv  Detail & Related papers  (2023-03-19T06:00:05Z)
• Improving the Model Consistency of Decentralized Federated Learning [68.2795379609854]
  Federated Learning (FL) discards the central server and each client only communicates with its neighbors in a decentralized communication network. Existing DFL suffers from inconsistency among local clients, which results in inferior compared to FLFL. We propose DFedSAMMGS, where $1lambda$ is the spectral gossip matrix and $Q$ is the number of sparse data gaps.
  arXiv  Detail & Related papers  (2023-02-08T14:37:34Z)
• Semi-Synchronous Personalized Federated Learning over Mobile Edge Networks [88.50555581186799]
  We propose a semi-synchronous PFL algorithm, termed as Semi-Synchronous Personalized FederatedAveraging (PerFedS$2$), over mobile edge networks. We derive an upper bound of the convergence rate of PerFedS2 in terms of the number of participants per global round and the number of rounds. Experimental results verify the effectiveness of PerFedS2 in saving training time as well as guaranteeing the convergence of training loss.
  arXiv  Detail & Related papers  (2022-09-27T02:12:43Z)
• Low-Latency Cooperative Spectrum Sensing via Truncated Vertical Federated Learning [51.51440623636274]
  We propose a vertical federated learning (VFL) framework to exploit the distributed features across multiple secondary users (SUs) without compromising data privacy. To accelerate the training process, we propose a truncated vertical federated learning (T-VFL) algorithm. The convergence performance of T-VFL is provided via mathematical analysis and justified by simulation results.
  arXiv  Detail & Related papers  (2022-08-07T10:39:27Z)
• Bayesian Federated Learning over Wireless Networks [87.37301441859925]
  Federated learning is a privacy-preserving and distributed training method using heterogeneous data sets stored at local devices. This paper presents an efficient modified BFL algorithm called scalableBFL (SBFL)
  arXiv  Detail & Related papers  (2020-12-31T07:32:44Z)

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.