Federated Edge Learning With Misaligned Over-the-Air Computation

Shao, Yulin; Gündüz, Deniz; Liew, Soung Chang

doi:10.1109/twc.2021.3125798

Cited by 56 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the perfect CSI at the users and accurate transmission timing, the signal overlapped from the devices to the server over-the-air naturally produces the arithmetic sum of the local model updates. To deal with residual channel gain and synchronization in AirComp, the authors in [175] referred to it as a misaligned AirComp and devised a sum-product maximum likelihood estimator to estimate the arithmetic sum of the transmitted symbols; the beamforming techniques were employed at the server to alleviate the destructive effects of the interference and noise terms due to the lack of CSI at the users and perfect CSI at the server [176], [177].…”

Section: Over-the-air Computationmentioning

confidence: 99%

Distributed Intelligence in Wireless Networks

Liu

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

The cloud-based solutions are becoming inefficient due to considerably large time delays, high power consumption, and security and privacy concerns caused by billions of connected wireless devices and typically zillions of bytes of data they produce at the network edge. A blend of edge computing and Artificial Intelligence (AI) techniques could optimally shift the resourceful computation servers closer to the network edge, which provides the support for advanced AI applications (e.g., video/audio surveillance and personal recommendation system) by enabling intelligent decision making on computing at the point of data generation as and when it is needed, and distributed Machine Learning (ML) with its potential to avoid the transmission of the large dataset and possible compromise of privacy that may exist in cloud-based centralized learning. Besides, the deployment of AI techniques to redesign end-to-end communication is attracting attention to improve communication performance. Therefore, the interaction of AI and wireless communications generates a new concept, named native AI wireless networks. In this paper, we conduct a comprehensive overview of recent advances in distributed intelligence in wireless networks under the umbrella of native AI wireless networks, with a focus on the design of distributed learning architectures for heterogeneous networks, on AI-enabled edge computing, on the communication-efficient technologies to support distributed learning, and on the AI-empowered end-to-end communications. We highlight the advantages of hybrid distributed learning architectures compared to state-of-the-art distributed learning techniques. We summarize the challenges of existing research contributions in distributed intelligence in wireless networks and identify potential future opportunities.

show abstract

Section: Over-the-air Computationmentioning

confidence: 99%

Distributed Intelligence in Wireless Networks

Liu

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…• Output: The output of the MLP is a vector ∆ w k,t that represents device k's local FL model update at current iteration t. Based on the predicted ∆ w k,t , the PS can adjust the transmit and receive beamforming matrices proactively to minimize problem (16).…”

Section: A Analysis Of the Convergence Of The Designed Flmentioning

confidence: 99%

“…However, the existence of the inverse function l −1 (•) defined in (8) significantly increases the complexity for solving (16). Considering l −1 (•) that is used to demodulate the symbols into numerical FL parameters, the minimization of the gap between l −1…”

Section: Optimization Of the Beamforming Matricesmentioning

confidence: 99%

“…Instead of decoding the individual local models of each device and then aggregating, AirComp allows edge devices to transmit their model parameters simultaneously over the same radio resources and decoding the average model (global model) directly at the PS [16]- [18]. However, most of these existing works, such as [19] and [20], focused on the use of AirComp for analog modulation due to its simplicity for FL convergence analysis, which may not be desirable for practical wireless communication systems that almost exclusively use digital modulations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-Layer Federated Learning Optimization in MIMO Networks

Wang¹,

Chen²,

Shen³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, the performance optimization of federated learning (FL), when deployed over a realistic wireless multiple-input multiple-output (MIMO) communication system with digital modulation and over-the-air computation (AirComp) is studied. In particular, an MIMO system is considered in which edge devices transmit their local FL models (trained using their locally collected data) to a parameter server (PS) using beamforming to maximize the number of devices scheduled for transmission. The PS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all devices. Due to the limited bandwidth in a wireless network, AirComp is adopted to enable efficient wireless data aggregation. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. To tackle this challenge, we propose a modified federated averaging (FedAvg) algorithm that combines digital modulation with AirComp to mitigate wireless fading while ensuring the communication efficiency. This is achieved by a joint transmit and receive beamforming design, which is formulated as a optimization problem to dynamically adjust the beamforming matrices based on current FL model parameters so as to minimize the transmitting error and ensure the FL performance. To achieve this goal, we first analytically characterize how the beamforming matrices affect the performance of the FedAvg in different iterations. Based on this relationship, an artificial neural network (ANN) is used to estimate the local FL models of all devices and adjust the beamforming matrices at the PS for future model transmission. The algorithmic advantages and improved performance of the proposed methodologies are demonstrated through extensive numerical experiments.

show abstract

“…For instance, in 5G systems, a 50 MHz channel with 15 KHz carrier spacing provides 3300 subcarriers during 10 ms [23]. Provided that we have accurate channel-gain precoding for phase compensation and strict synchronization among the participating devices [24], in the model upload stage of the tth round, each device i first designs the transmitted signal as e −jφ t i x t i , where e −jφ t i is the local phase correction performed by the device i. Then, each coordinate of the local model update is assigned to a specific subcarrier and then transmitted via a wireless MAC simultaneously.…”

Section: Wireless Communication Modelmentioning

confidence: 99%

Energy-efficient Federated Edge Learning for Internet of Vehicles via Rate-Splitting Multiple Access

Zhang

Yeung

2022

2022 International Symposium on Wireless Communication Systems (ISWCS)

View full text Add to dashboard Cite

Federated Learning (FL) is a collaborative learning framework that enables edge devices to collaboratively learn a global model while keeping raw data locally. Although FL avoids leaking direct information from local datasets, sensitive information can still be inferred from the shared models. To address the privacy issue in FL, differential privacy (DP) mechanisms are leveraged to provide formal privacy guarantee. However, when deploying FL at the wireless edge with over-the-air computation, ensuring client-level DP faces significant challenges. In this paper, we propose a novel wireless FL scheme called private federated edge learning with sparsification (PFELS) to provide client-level DP guarantee with intrinsic channel noise while reducing communication and energy overhead and improving model accuracy. The key idea of PFELS is for each device to first compress its model update and then adaptively design the transmit power of the compressed model update according to the wireless channel status without any artificial noise addition. We provide a privacy analysis for PFELS and prove the convergence of PFELS under general non-convex and non-IID settings. Experimental results show that compared with prior work, PFELS can improve the accuracy with the same DP guarantee and save communication and energy costs simultaneously.

show abstract

Federated Edge Learning With Misaligned Over-the-Air Computation

Cited by 56 publications

References 28 publications

Distributed Intelligence in Wireless Networks

Distributed Intelligence in Wireless Networks

Cross-Layer Federated Learning Optimization in MIMO Networks

Energy-efficient Federated Edge Learning for Internet of Vehicles via Rate-Splitting Multiple Access

Contact Info

Product

Resources

About