Imperial College London

ProfessorDenizGunduz

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Professor in Information Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6218d.gunduz Website

 
 
//

Assistant

 

Ms Joan O'Brien +44 (0)20 7594 6316

 
//

Location

 

1016Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

314 results found

Chen M, Gunduz D, Huang K, Saad W, Bennis M, Feljan AV, Poor HVet al., 2021, Guest Editorial Special Issue on Distributed Learning Over Wireless Edge Networks-Part I, IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, Vol: 39, Pages: 3575-3578, ISSN: 0733-8716

Journal article

Chen M, Gunduz D, Huang K, Saad W, Bennis M, Feljan AV, Poor HVet al., 2021, Distributed Learning in Wireless Networks: Recent Progress and Future Challenges, IEEE Journal on Selected Areas in Communications, Vol: 39, Pages: 3579-3605, ISSN: 0733-8716

The next-generation of wireless networks will enable many machine learning (ML) tools and applications to efficiently analyze various types of data collected by edge devices for inference, autonomy, and decision making purposes. However, due to resource constraints, delay limitations, and privacy challenges, edge devices cannot offload their entire collected datasets to a cloud server for centrally training their ML models or inference purposes. To overcome these challenges, distributed learning and inference techniques have been proposed as a means to enable edge devices to collaboratively train ML models without raw data exchanges, thus reducing the communication overhead and latency as well as improving data privacy. However, deploying distributed learning over wireless networks faces several challenges including the uncertain wireless environment (e.g., dynamic channel and interference), limited wireless resources (e.g., transmit power and radio spectrum), and hardware resources (e.g., computational power). This paper provides a comprehensive study of how distributed learning can be efficiently and effectively deployed over wireless edge networks. We present a detailed overview of several emerging distributed learning paradigms, including federated learning, federated distillation, distributed inference, and multi-agent reinforcement learning. For each learning framework, we first introduce the motivation for deploying it over wireless networks. Then, we present a detailed literature review on the use of communication techniques for its efficient deployment. We then introduce an illustrative example to show how to optimize wireless networks to improve its performance. Finally, we introduce future research opportunities. In a nutshell, this paper provides a holistic set of guidelines on how to deploy a broad range of distributed learning frameworks over real-world wireless communication networks.

Journal article

Mital N, Kralevska K, Ling C, Gunduz Det al., 2021, Functional Broadcast Repair of Multiple Partial Failures in Wireless Distributed Storage Systems, IEEE Journal on Selected Areas in Information Theory, Vol: 2, Pages: 1093-1107

Journal article

Erkip E, Gunduz D, Ioannidis S, Kliewer J, Malak D, Medard M, Srikant Ret al., 2021, JSAIT Editorial for the Special Issue on “Beyond Errors and Erasures: Coding for Data Management and Delivery in Networks”, IEEE Journal on Selected Areas in Information Theory, Vol: 2, Pages: 1075-1077

Journal article

Sun Y, Zhou S, Niu Z, Gunduz Det al., 2021, Dynamic scheduling for over-the-air federated edge learning with energy constraints, IEEE Journal on Selected Areas in Communications, Vol: 40, Pages: 227-242, ISSN: 0733-8716

Machine learning and wireless communication technologies are jointly facilitating an intelligent edge, where federated edge learning (FEEL) is emerging as a promising training framework. As wireless devices involved in FEEL are resource limited in terms of communication bandwidth, computing power and battery capacity, it is important to carefully schedule them to optimize the training performance. In this work, we consider an over-the-air FEEL system with analog gradient aggregation, and propose an energy-aware dynamic device scheduling algorithm to optimize the training performance within the energy constraints of devices, where both communication energy for gradient aggregation and computation energy for local training are considered. The consideration of computation energy makes dynamic scheduling challenging, as devices are scheduled before local training, but the communication energy for over-the-air aggregation depends on the l2-norm of local gradient, which is known only after local training. We thus incorporate estimation methods into scheduling to predict the gradient norm. Taking the estimation error into account, we characterize the performance gap between the proposed algorithm and its offline counterpart. Experimental results show that, under a highly unbalanced local data distribution, the proposed algorithm can increase the accuracy by 4.9% on CIFAR-10 dataset compared with the myopic benchmark, while satisfying the energy constraints.

Journal article

Mashhadi MB, Jankowski M, Tung T-Y, Kobus S, Gunduz Det al., 2021, Federated mmWave beam selection utilizing LIDAR data, IEEE Wireless Communications Letters, Vol: 10, Pages: 2269-2273, ISSN: 2162-2337

Efficient link configuration in millimeter wave (mmWave) communication systems is a crucial yet challenging task due to the overhead imposed by beam selection. For vehicle-to-infrastructure (V2I) networks, side information from LIDAR sensors mounted on the vehicles has been leveraged to reduce the beam search overhead. In this letter, we propose a federated LIDAR aided beam selection method for V2I mmWave communication systems. In the proposed scheme, connected vehicles collaborate to train a shared neural network (NN) on their locally available LIDAR data during normal operation of the system. We also propose a reduced-complexity convolutional NN (CNN) classifier architecture and LIDAR preprocessing, which significantly outperforms previous works in terms of both the performance and the complexity.

Journal article

Mashhadi MB, Gunduz D, 2021, Pruning the pilots: deep learning-based pilot design and channel estimation for MIMO-OFDM systems, IEEE Transactions on Wireless Communications, Vol: 20, Pages: 6315-6328, ISSN: 1536-1276

With the large number of antennas and subcarriers the overhead due to pilot transmission for channel estimation can be prohibitive in wideband massive multiple-input multiple-output (MIMO) systems. This can degrade the overall spectral efficiency significantly, and as a result, curtail the potential benefits of massive MIMO. In this paper, we propose a neural network (NN)-based joint pilot design and downlink channel estimation scheme for frequency division duplex (FDD) MIMO orthogonal frequency division multiplex (OFDM) systems. The proposed NN architecture uses fully connected layers for frequency-aware pilot design, and outperforms linear minimum mean square error (LMMSE) estimation by exploiting inherent correlations in MIMO channel matrices utilizing convolutional NN layers. Our proposed NN architecture uses a non-local attention module to learn longer range correlations in the channel matrix to further improve the channel estimation performance.We also propose an effective pilot reduction technique by gradually pruning less significant neurons from the dense NN layers during training. This constitutes a novel application of NN pruning to reduce the pilot transmission overhead. Our pruning-based pilot reduction technique reduces the overhead by allocating pilots across subcarriers non-uniformly and exploiting the inter-frequency and inter-antenna correlations in the channel matrix efficiently through convolutional layers and attention module.

Journal article

Faqir OJ, Kerrigan EC, Gunduz D, 2021, Accuracy-awareness: A pessimistic approach to optimal control of triggered mobile communication networks, 7th IFAC Conference on Nonlinear Model Predictive Control (NMPC), Publisher: ELSEVIER, Pages: 296-301, ISSN: 2405-8963

We use nonlinear model predictive control to procure a joint control of mobility and transmission to minimize total network communication energy use. The nonlinear optimization problem is solved numerically in a self-triggered framework, where the next control update time depends on the predicted state trajectory and the accuracy of the numerical solution. Solution accuracy must be accounted for in any circumstance where systems are run in open-loop for long stretches of time based on potentially inaccurate predictions. These triggering conditions allow us to place wireless nodes in low energy ‘idle’ states for extended periods, saving over 70% of energy compared to a periodic policy where nodes consistently use energy to receive control updates.

Conference paper

Malekzadeh M, Borovykh A, Gunduz D, 2021, Honest-but-curious nets: sensitive attributes of private inputs can be secretly coded into the classifiers' outputs, ACM CCS 2021, Publisher: ACM

It is known that deep neural networks, trained for the classification of non-sensitive target attributes, can reveal sensitive attributes of their input data through internal representations extracted by the classifier. We take a step forward and show that deep classifiers can be trained to secretly encode a sensitive attribute of their input data into the classifier's outputs for the target attribute, at inference time. Our proposed attack works even if users have a full white-box view of the classifier, can keep all internal representations hidden, and only release the classifier's estimations for the target attribute. We introduce an information-theoretical formulation for such attacks and present efficient empirical implementations for training honest-but-curious (HBC) classifiers: classifiers that can be accurate in predicting their target attribute, but can also exploit their outputs to secretly encode a sensitive attribute. Our work highlights a vulnerability that can be exploited by malicious machine learning service providers to attack their user's privacy in several seemingly safe scenarios; such as encrypted inferences, computations at the edge, or private knowledge distillation. Experimental results on several attributes in two face-image datasets show that a semi-trusted server can train classifiers that are not only perfectly honest but also accurately curious. We conclude by showing the difficulties in distinguishing between standard and HBC classifiers, discussing challenges in defending against this vulnerability of deep classifiers, and enumerating related open directions for future studies.

Conference paper

Gindullina E, Badia L, Gunduz D, 2021, Age-of-information with information source diversity in an energy harvesting system, IEEE Transactions on Green Communications and Networking, Vol: 5, Pages: 1529-1540, ISSN: 2473-2400

Age of information (AoI) is a key performance metric for the Internet of things (IoT). Timely status updates are essential for many IoT applications; however, they often suffer from harsh energy constraints and the unreliability of underlying information sources. To overcome these unpredictabilities, one can employ multiple sources that track the same process of interest, but with different energy costs and reliabilities. We consider an energy-harvesting (EH) monitoring node equipped with a finite-size battery and collecting status updates from multiple heterogeneous information sources. We investigate the policies that minimize the average AoI, formulating a Markov decision process (MDP) to choose the optimal actions of either updating from one of the sources or remaining idle, based on the current energy level and the AoI at the monitoring node. We analyze the structure of the optimal solution for different cost/AoI distribution combinations, and compare its performance with an aggressive policy that transmits whenever possible.

Journal article

Hasircioglu B, Gomez-Vilardebo J, Gunduz D, 2021, Bivariate Polynomial Coding for Efficient Distributed Matrix Multiplication, IEEE Journal on Selected Areas in Information Theory, Vol: 2, Pages: 814-829

Journal article

Amiri MM, Gunduz D, Kulkarni SR, Vincent Poor Het al., 2021, Convergence of federated learning over a noisy downlink, IEEE Transactions on Wireless Communications, ISSN: 1536-1276

We study federated learning (FL), where power-limited wireless devices utilize their local datasets to collaboratively train a global model with the help of a remote parameter server (PS). The PS has access to the global model and shares it with the devices for local training using their datasets, and the devices return the result of their local updates to the PS to update the global model. The algorithm continues until the convergence of the global model. This framework requires downlink transmission from the PS to the devices and uplink transmission from the devices to the PS. The goal of this study is to investigate the impact of the bandwidth-limited shared wireless medium on the performance of FL with a focus on the downlink. To this end, the downlink and uplink channels are modeled as fading broadcast and multiple access channels, respectively, both with limited bandwidth. For downlink transmission, we first introduce a digital approach, where a quantization technique is employed at the PS followed by a capacity-achieving channel code to transmit the global model update over the wireless broadcast channel at a common rate such that all the devices can decode it. Next, we propose analog downlink transmission, where the global model is broadcast by the PS in an uncoded manner. We consider analog transmission over the uplink in both cases, since its superiority over digital transmission for uplink has been well studied in the literature. We further analyze the convergence behavior of the proposed analog transmission approach over the downlink assuming that the uplink transmission is error-free. Numerical experiments show that the analog downlink approach provides significant improvement over the digital one with a more notable improvement when the data distribution across the devices is not independent and identically distributed. The experimental results corroborate the convergence analysis, and show that a smaller number of local iterations should be used when

Journal article

Li GY, Saad W, Ozgur A, Kairouz P, Qin Z, Hoydis J, Han Z, Gunduz D, Elmirghani Jet al., 2021, Series Editorial: The Third Issue of the Series on Machine Learning in Communications and Networks, IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, Vol: 39, Pages: 2267-2270, ISSN: 0733-8716

Journal article

Amiri MM, Duman TM, Gunduz D, Kulkarni SR, Poor HVet al., 2021, Blind federated edge learning, IEEE Transactions on Wireless Communications, Vol: 20, Pages: 5129-5143, ISSN: 1536-1276

We study federated edge learning (FEEL), where wireless edge devices, each with its own dataset, learn a global model collaboratively with the help of a wireless access point acting as the parameter server (PS). At each iteration, wireless devices perform local updates using their local data and the most recent global model received from the PS, and send their local updates to the PS over a wireless fading multiple access channel (MAC). The PS then updates the global model according to the signal received over the wireless MAC, and shares it with the devices. Motivated by the additive nature of the wireless MAC, we propose an analog `over-the-air' aggregation scheme, in which the devices transmit their local updates in an uncoded fashion. However, unlike recent literature on over-the-air FEEL, here we assume that the devices do not have channel state information (CSI), while the PS has imperfect CSI. On the other hand, the PS is equipped with multiple antennas to alleviate the destructive effect of the channel, exacerbated due to the lack of perfect CSI. We design a receive beamforming scheme at the PS, and show that it can compensate for the lack of perfect CSI when the PS has a sufficient number of antennas. We also derive the convergence rate of the proposed algorithm highlighting the impact of the lack of perfect CSI, as well as the number of PS antennas. Both the experimental results and the convergence analysis illustrate the performance improvement of the proposed algorithm with the number of PS antennas, where the wireless fading MAC becomes deterministic despite the lack of perfect CSI when the PS has a sufficiently large number of antennas.

Journal article

Tung T-Y, Kobus S, Roig JP, Gunduz Det al., 2021, Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels, IEEE Journal on Selected Areas in Communications, Vol: 39, Pages: 2590-2603, ISSN: 0733-8716

We propose a novel formulation of the “effectivenessproblem” in communications, put forth by Shannon and Weaverin their seminal work “The Mathematical Theory of Communication”, by considering multiple agents communicating overa noisy channel in order to achieve better coordination andcooperation in a multi-agent reinforcement learning (MARL)framework. Specifically, we consider a multi-agent partiallyobservable Markov decision process (MA-POMDP), in which theagents, in addition to interacting with the environment, can alsocommunicate with each other over a noisy communication channel. The noisy communication channel is considered explicitlyas part of the dynamics of the environment, and the messageeach agent sends is part of the action that the agent can take.As a result, the agents learn not only to collaborate with eachother but also to communicate “effectively” over a noisy channel.This framework generalizes both the traditional communicationproblem, where the main goal is to convey a message reliably overa noisy channel, and the “learning to communicate” frameworkthat has received recent attention in the MARL literature, wherethe underlying communication channels are assumed to be errorfree. We show via examples that the joint policy learned using theproposed framework is superior to that where the communicationis considered separately from the underlying MA-POMDP. Thisis a very powerful framework, which has many real worldapplications, from autonomous vehicle planning to drone swarmcontrol, and opens up the rich toolbox of deep reinforcementlearning for the design of multi-user communication systems.

Journal article

Li GY, Saad W, Ozgur A, Kairouz P, Qin Z, Hoydis J, Han Z, Gunduz D, Elmirghani Jet al., 2021, Series Editorial: The Second Issue of the Series on Machine Learning in Communications and Networks, IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, Vol: 39, Pages: 1855-1857, ISSN: 0733-8716

Journal article

Kurka DB, Gunduz D, 2021, Bandwidth-Agile Image Transmission with Deep Joint Source-Channel Coding, IEEE Transactions on Wireless Communications, Pages: 1-1, ISSN: 1536-1276

We propose deep learning based communication methods for adaptive-bandwidth transmission of images over wireless channels. We consider the scenario in which images are transmitted progressively in layers over time or frequency, and such layers can be aggregated by receivers in order to increase the quality of their reconstructions. We investigate two scenarios, one in which the layers are sent sequentially, and incrementally contribute to the refinement of a reconstruction, and another in which the layers are independent and can be retrieved in any order. Those scenarios correspond to the well known problems of successive refinement and multiple descriptions, respectively, in the context of joint source-channel coding (JSCC). We propose DeepJSCC-l, an innovative solution that uses convolutional autoencoders, and present three architectures with different complexity trade-offs. To the best of our knowledge, this is the first practical multiple-description JSCC scheme developed and tested for practical information sources and channels. Numerical results show that DeepJSCC-l can learn to transmit the source progressively with negligible losses in the end-to-end performance compared with a single transmission. Moreover, DeepJSCC-l has comparable performance with state of the art digital progressive transmission schemes in the challenging low signal-to-noise ratio (SNR) and small bandwidth regimes, with the additional advantage of graceful degradation with channel SNR.

Journal article

Amiria MM, Gunduzb D, Kulkarni SR, Vincent Poor Het al., 2021, Convergence of update aware device scheduling for federated learning at the wireless edge, IEEE Transactions on Wireless Communications, Vol: 20, Pages: 3643-3658, ISSN: 1536-1276

We study federated learning (FL) at the wireless edge, where power-limited devices with local datasets collaboratively train a joint model with the help of a remote parameter server (PS). We assume that the devices are connected to the PS through a bandwidth-limited shared wireless channel. At each iteration of FL, a subset of the devices are scheduled to transmit their local model updates to the PS over orthogonal channel resources, while each participating device must compress its model update to accommodate to its link capacity. We design novel scheduling and resource allocation policies that decide on the subset of the devices to transmit at each round, and how the resources should be allocated among the participating devices, not only based on their channel conditions, but also on the significance of their local model updates. We then establish convergence of a wireless FL algorithm with device scheduling, where devices have limited capacity to convey their messages. The results of numerical experiments show that the proposed scheduling policy, based on both the channel conditions and the significance of the local model updates, provides a better long-term performance than scheduling policies based only on either of the two metrics individually. Furthermore, we observe that when the data is independent and identically distributed (i.i.d.) across devices, selecting a single device at each round provides the best performance, while when the data distribution is non-i. i.d., scheduling multiple devices at each round improves the performance. This observation is verified by the convergence result, which shows that the number of scheduled devices should increase for a less diverse and more biased data distribution.

Journal article

Ceran E, Gunduz D, Gyorgy A, 2021, A reinforcement learning approach to age of information in multi-user networks with HARQ‌, IEEE Journal on Selected Areas in Communications, Vol: 39, Pages: 1412-1426, ISSN: 0733-8716

Scheduling the transmission of time-sensitive information from a source node to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of information (AoI) at the users. A long-term average resource constraint is imposed on the source, which limits the average number of transmissions. The source can transmit only to a single user at each time slot, and after each transmission, it receives an instantaneous ACK/NACK feedback from the intended receiver, and decides when and to which user to transmit the next update. Assuming the channel statistics are known, the optimal scheduling policy is studied for both the standard automatic repeat request (ARQ) and hybrid ARQ (HARQ) protocols. Then, a reinforcement learning (RL) approach is introduced to find a near-optimal policy, which does not assume any a priori information on the random processes governing the channel states. Different RL methods including average-cost SARSA with linear function approximation (LFA), upper confidence reinforcement learning (UCRL2), and deep Q-network (DQN) are applied and compared through numerical simulations.

Journal article

Mashhadi MB, Yang Q, Gunduz D, 2021, Distributed deep convolutional compression for massive MIMO CSI feedback, IEEE Transactions on Wireless Communications, Vol: 20, Pages: 2621-2633, ISSN: 1536-1276

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO network, each user needs to compress and feedback its downlink CSI to the BS. The CSI overhead scales with the number of antennas, users and subcarriers, and becomes a major bottleneck for the overall spectral efficiency. In this paper, we propose a deep learning (DL)-based CSI compression scheme, called DeepCMC, composed of convolutional layers followed by quantization and entropy coding blocks. In comparison with previous DL-based CSI reduction structures, DeepCMC proposes a novel fully-convolutional neural network (NN) architecture, with residual layers at the decoder, and incorporates quantization and entropy coding blocks into its design. DeepCMC is trained to minimize a weighted rate-distortion cost, which enables a trade-off between the CSI quality and its feedback overhead. Simulation results demonstrate that DeepCMC outperforms the state of the art CSI compression schemes in terms of the reconstruction quality of CSI for the same compression rate. We also propose a distributed version of DeepCMC for a multi-user MIMO scenario to encode and reconstruct the CSI from multiple users in a distributed manner. Distributed DeepCMC not only utilizes the inherent CSI structures of a single MIMO user for compression, but also benefits from the correlations among the channel matrices of nearby users to further improve the performance in comparison with DeepCMC. We also propose a reduced-complexity training method for distributed DeepCMC, allowing to scale it to multiple users, and suggest a cluster-based distributed DeepCMC approach for practical implementation.

Journal article

Rassouli B, Gunduz D, 2021, On perfect privacy, IEEE Journal on Selected Areas in Information Theory, Vol: 2, Pages: 177-191, ISSN: 2641-8770

The problem of private data disclosure is studied from an informationtheoretic perspective. Considering a pair of dependent random variables$(X,Y)$, where $X$ and $Y$ denote the private and useful data, respectively,the following problem is addressed: What is the maximum information that can berevealed about $Y$ (measured by mutual information $I(Y;U)$, in which $U$ isthe revealed data), while disclosing no information about $X$ (captured by thecondition of statistical independence, i.e., $X\independent U$, and henceforth,called \textit{perfect privacy})? We analyze the supremization of\textit{utility}, i.e., $I(Y;U)$ under the condition of perfect privacy for twoscenarios: \textit{output perturbation} and \textit{full data observation}models, which correspond to the cases where a Markov kernel, called\textit{privacy-preserving mapping}, applies to $Y$ and the pair $(X,Y)$,respectively. When both $X$ and $Y$ have a finite alphabet, the linearalgebraic analysis involved in the solution provides some interesting results,such as upper/lower bounds on the size of the released alphabet and the maximumutility. Afterwards, it is shown that for the jointly Gaussian $(X,Y)$, perfectprivacy is not possible in the output perturbation model in contrast to thefull data observation model. Finally, an asymptotic analysis is provided toobtain the rate of released information when a sufficiently small leakage isallowed. In particular, in the context of output perturbation model, it isshown that this rate is always finite when perfect privacy is not feasible, andtwo lower bounds are provided for it; When perfect privacy is feasible, it isshown that under mild conditions, this rate becomes unbounded.

Journal article

Buyukates B, Ozfatura E, Ulukus S, Gunduz Det al., 2021, Gradient Coding with Dynamic Clustering for Straggler Mitigation, IEEE International Conference on Communications (ICC), Publisher: IEEE, ISSN: 1550-3607

Conference paper

Li GY, Saad W, Ozgur A, Kairouz P, Qin Z, Hoydis J, Han Z, Gunduz D, Elmirghani Jet al., 2021, Series editorial: inauguration issue of the series on machine learning in communications and networks, IEEE Journal on Selected Areas in Communications, Vol: 39, Pages: 1-3, ISSN: 0733-8716

In the era of the new generation of communication systems, data traffic is expected to continuously strain the capacity of future communication networks. Along with the remarkable growth in data traffic, new applications, such as wearable devices, autonomous systems, and the Internet of Things (IoT), continue to emerge and generate even more data traffic with vastly different requirements. This growth in the application domain brings forward an inevitable need for more intelligent processing, operation, and optimization of future communication networks.

Journal article

Jankowski M, Gunduz D, Mikolajczyk K, 2021, Wireless image retrieval at the edge, IEEE Journal on Selected Areas in Communications, Vol: 39, Pages: 89-100, ISSN: 0733-8716

We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge server. These can be images of the same person or a vehicle taken from other cameras at different times and locations. Our goal is to maximize the accuracy of the retrieval task under power and bandwidth constraints over the wireless link. Due to the stringent delay constraint of the underlying application, sending the whole image at a sufficient quality is not possible. We propose two alternative schemes based on digital and analog communications, respectively. In the digital approach, we first propose a deep neural network (DNN) aided retrieval-oriented image compression scheme, whose output bit sequence is transmitted over the channel using conventional channel codes. In the analog joint source and channel coding (JSCC) approach, the feature vectors are directly mapped into channel symbols. We evaluate both schemes on image based re-identification (re-ID) tasks under different channel conditions, including both static and fading channels. We show that the JSCC scheme significantly increases the end-to-end accuracy, speeds up the encoding process, and provides graceful degradation with channel conditions. The proposed architecture is evaluated through extensive simulations on different datasets and channel conditions, as well as through ablation studies.

Journal article

Ozfatura E, Ulukus S, Gunduz D, 2021, Coded Distributed Computing with Partial Recovery, IEEE Transactions on Information Theory, ISSN: 0018-9448

Coded computation techniques provide robustness against straggling workers in distributed computing. However, most of the existing schemes require exact provisioning of the straggling behavior and ignore the computations carried out by straggling workers. Moreover, these schemes are typically designed to recover the desired computation results accurately, while in many machine learning and iterative optimization algorithms, faster approximate solutions are known to result in an improvement in the overall convergence time. In this paper, we first introduce a novel coded matrix-vector multiplication scheme, called coded computation with partial recovery (CCPR), which benefits from the advantages of both coded and uncoded computation schemes, and reduces both the computation time and the decoding complexity by allowing a trade-off between the accuracy and the speed of computation. We then extend this approach to distributed implementation of more general computation tasks by proposing a coded communication scheme with partial recovery, where the results of subtasks computed by the workers are coded before being communicated. Numerical simulations on a large linear regression task confirm the benefits of the proposed scheme in terms of the trade-off between the computation accuracy and latency.

Journal article

Hasircioglu B, Gunduz D, 2021, PRIVATE WIRELESS FEDERATED LEARNING WITH ANONYMOUS OVER-THE-AIR COMPUTATION, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 5195-5199

Conference paper

Ozfatura E, Ozfatura K, Gunduz D, 2021, Time-Correlated Sparsification for Communication-Efficient Federated Learning, IEEE International Symposium on Information Theory (ISIT), Publisher: IEEE, Pages: 461-466

Conference paper

Hasircioglu B, Gomez-Vilardebo J, Gunduz D, 2021, Speeding Up Private Distributed Matrix Multiplication via Bivariate Polynomial Codes, IEEE International Symposium on Information Theory (ISIT), Publisher: IEEE, Pages: 1853-1858

Conference paper

Xia J, Gunduz D, 2021, Meta-learning Based Beamforming Design for MISO Downlink, IEEE International Symposium on Information Theory (ISIT), Publisher: IEEE, Pages: 2954-2959

Conference paper

Ozfatura E, Ozfatura K, Gunduz D, 2021, FedADC: Accelerated Federated Learning with Drift Control, IEEE International Symposium on Information Theory (ISIT), Publisher: IEEE, Pages: 467-472

Conference paper

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=00761710&limit=30&person=true