Communication over noisy channels relies on error-correcting codes (ECCs) tailored to system constraints. Neural decoders can improve ECC reliability, yet their high computational complexity hinders practical deployment. We instead design a transformer-based transmission scheme that improves the reliability of existing ECCs without replacing them. We call this approach TransCoder, alluding both to its function and architecture. TransCoder operates as a code-adaptive module deployable at the transmitter, the receiver, or both. A block-attention neural decoder iteratively refines the channel observations together with the soft outputs of a conventional decoder. Across LDPC, BCH, Polar, and Turbo codes and a wide SNR range, TransCoder significantly lowers the block error rate (BLER) at complexity comparable to conventional decoders. Gains are largest at moderate blocklengths (64-512) and lower rates, regimes in which existing neural decoders struggle despite their much higher complexity. For 5G NR LDPC codes with blocklengths ≥400, the decoder-only variant still achieves significant performance improvements, especially at high SNR. These results position TransCoder as a practical solution for resource-constrained wireless devices.

We introduce deep joint source-channel coding (DeepJSCC) schemes for image transmission over cooperative relay channels. The relay either amplifies-and-forwards its received signal, called DeepJSCC-AF, or leverages neural networks to extract relevant features from its received signal, called DeepJSCC-PF (Process-and-Forward). We consider both half- and full-duplex relays, and propose a novel transformer-based model at the relay. For a half-duplex relay, it is shown that the proposed scheme learns to generate correlated signals at the relay and source to obtain beamforming gains. In the full-duplex case, we introduce a novel block-based transmission strategy, in which the source transmits in blocks, and the relay updates its knowledge about the input signal after each block and generates its own signal. To enhance practicality, a single transformer-based model is used at the relay at each block, together with an adaptive transmission module, which allows the model to seamlessly adapt to different channel qualities and the transmission powers. Simulation results demonstrate the superior performance of DeepJSCC-PF compared to the state-of-the-art BPG image compression algorithm operating at the maximum achievable rate of conventional decode-and-forward and compress-and-forward protocols, in both half- and full-duplex relay scenarios over AWGN and Rayleigh fading channels.

The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients’ models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks.

This paper presents a novel wireless image transmission paradigm that can exploit feedback from the receiver, called JSCCformer-f. We consider a block feedback channel model, where the transmitter receives noiseless/noisy channel output feedback after each block. The proposed scheme employs a single encoder to facilitate transmission over multiple blocks, refining the receiver’s estimation at each block. Specifically, the unified encoder of JSCCformer-f can leverage the semantic information from the source image, and acquire channel state information and the decoder’s current belief about the source image from the feedback signal to generate coded symbols at each block. Numerical experiments show that our JSCCformer-f scheme achieves state-of-the-art performance with robustness to noise in the feedback link. Additionally, JSCCformer-f can adapt to the channel condition directly through feedback without the need for separate channel estimation. We further extend the scope of the JSCCformer-f approach to include the broadcast channel, which enables the transmitter to generate broadcast codes in accordance with signal semantics and channel feedback from individual receivers.

Intermittent connectivity of clients to the parameter server (PS) is a major bottleneck in federated edge learning frameworks. The lack of constant connectivity induces a large generalization gap, especially when the local data distribution amongst clients exhibits heterogeneity. To overcome intermittent communication outages between clients and the central PS, we introduce the concept of collaborative relaying wherein the participating clients relay their neighbors’ local updates to the PS in order to boost the participation of clients with poor connectivity to the PS. We propose a semi-decentralized federated learning framework in which at every communication round, each client initially computes a local averaging of a subset of its neighboring clients’ updates, and eventually transmits to the PS a weighted average of its own update and those of its neighbors’. We appropriately optimize these local averaging weights to ensure that the global update at the PS is unbiased with minimal variance – consequently improving the convergence rate. Numerical evaluations on the CIFAR-10 dataset demonstrate that our collaborative relaying approach outperforms federated averaging-based benchmarks for learning over intermittently-connected networks such as when the clients communicate over millimeter wave channels with intermittent blockages.

Deep neural network (DNN)-assisted channel coding designs, such as low-complexity neural decoders for existing codes, or end-to-end neural-network-based auto-encoder designs are gaining interest recently due to their improved performance and flexibility; particularly for communication scenarios in which high-performing structured code designs do not exist. Communication in the presence of feedback is one such communication scenario, and practical code design for feedback channels has remained an open challenge in coding theory for many decades. Recently, DNN-based designs have shown impressive results in exploiting feedback. In particular, generalized block attention feedback (GBAF) codes, which utilizes the popular transformer architecture, achieved significant improvement in terms of the block error rate (BLER) performance. However, previous works have focused mainly on passive feedback, where the transmitter observes a noisy version of the signal at the receiver. In this work, we show that GBAF codes can also be used for channels with active feedback. We implement a pair of transformer architectures, at the transmitter and the receiver, which interact with each other sequentially, and achieve a new state-of-the-art BLER performance, especially in the low SNR regime.

Distributed implementations are crucial in speeding up large scale machine learning applications. Distributed gradient descent (GD) is widely employed to parallelize the learning task by distributing the dataset across multiple workers. A significant performance bottleneck for the per-iteration completion time in distributed synchronous GD is straggling workers. Coded distributed computation techniques have been introduced recently to mitigate stragglers and to speed up GD iterations by assigning redundant computations to workers. In this paper, we introduce a novel paradigm of dynamic coded computation, which assigns redundant data to workers to acquire the flexibility to dynamically choose from among a set of possible codes depending on the past straggling behavior. In particular, we propose gradient coding (GC) with dynamic clustering, called GC-DC, and regulate the number of stragglers in each cluster by dynamically forming the clusters at each iteration. With time-correlated straggling behavior, GC-DC adapts to the straggling behavior over time; in particular, at each iteration, GC-DC aims at distributing the stragglers across clusters as uniformly as possible based on the past straggler behavior. For both homogeneous and heterogeneous worker models, we numerically show that GC-DC provides significant improvements in the average per-iteration completion time without an increase in the communication load compared to the original GC scheme.

Ultra-reliable short-packet communication is a major challenge in future wireless networks with critical applications. To achieve ultra-reliable communications beyond 99.999%, this paper envisions a new interaction-based communication paradigm that exploits feedback from the receiver. We present AttentionCode, a new class of feedback codes leveraging deep learning (DL) technologies. The underpinnings of AttentionCode are three architectural innovations: AttentionNet, input restructuring, and adaptation to fading channels, accompanied by several training methods, including large-batch training, distributed learning, look-ahead optimizer, training-test signal-to-noise ratio (SNR) mismatch, and curriculum learning. The training methods can potentially be generalized to other wireless communication applications with machine learning. Numerical experiments verify that AttentionCode establishes a new state of the art among all DL-based feedback codes in both additive white Gaussian noise (AWGN) channels and fading channels. In AWGN channels with noiseless feedback, for example, AttentionCode achieves a block error rate (BLER) of 10−7 when the forward channel SNR is 0 dB for a block size of 50 bits, demonstrating the potential of AttentionCode to provide ultra-reliable short-packet communications.

We present a semi-decentralized federated learning algorithm wherein clients collaborate by relaying their neighbors’ local updates to a central parameter server (PS). At every communication round to the PS, each client computes a local consensus of the updates from its neighboring clients and eventually transmits a weighted average of its own update and those of its neighbors to the PS. We appropriately optimize these averaging weights to ensure that the global update at the PS is unbiased and to reduce the variance of the global update at the PS, consequently improving the rate of convergence. Numerical simulations substantiate our theoretical claims and demonstrate settings with intermittent connectivity between the clients and the PS, where our proposed algorithm shows an improved convergence rate and accuracy in comparison with the federated averaging algorithm.

Proactive content caching at user devices and coded delivery is studied for a non-uniform file popularity distribution. A novel centralized uncoded caching and coded delivery scheme, calledcross-level coded delivery (CLCD), is proposed, which can be applied to large file libraries under non-uniform demands. In the CLCD scheme, the same sub-packetization is used for all the files in the library in order to prevent additional zero-padding in the delivery phase, and unlike the existing schemes in the literature, users requesting files from different popularity groups can still be served by the same multicast message in order to reduce the delivery rate. Simulation results indicate more than 10% reduction in the average delivery rate for typical Zipf distribution parameter values.

Coded computation techniques provide robustness againststragglingworkers 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, calledcoded 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.

In distributed synchronous gradient descent (GD) the main performance bottleneck for the per-iteration completion time is the slowest straggling workers. To speed up GD iterations in the presence of stragglers, coded distributed computation techniques are implemented by assigning redundant computations to workers. In this paper, we propose a novel gradient coding (GC) scheme that utilizes dynamic clustering, denoted by GC-DC, to speed up gradient calculations. Under time-correlated straggling behavior, GC-DC aims at regulating the number of straggling workers in each cluster based on the straggler behavior in the previous iteration. We numerically show that GC-DC provides significant improvements in the average completion time (of each iteration) with no increase in the communication load compared to the original GC scheme.

Federated learning (FL) enables multiple clients to collaboratively train a shared model, with the help of a parameter server (PS), without disclosing their local datasets. However, due to the increasing size of the trained models, the communication load due to the iterative exchanges between the clients and the PS often becomes a bottleneck in the performance. Sparse communication is often employed to reduce the communication load, where only a small subset of the model updates are communicated from the clients to the PS. In this paper, we introduce a novel time-correlated sparsification (TCS) scheme, which builds upon the notion that sparse communication framework can be considered as identifying the most significant elements of the underlying model. Hence, TCS exploits the correlation between the sparse representations at consecutive iterations in FL, so that the overhead due to encoding of the sparse representation can be significantly reduced without compromising the test accuracy. Through extensive simulations on the CIFAR-10 dataset, we show that TCS can achieve centralized training accuracy with 100 times sparsification, and up to 2000 times reduction in the communication load when employed with quantization.

Federated learning (FL) has become de facto framework for collaborative learning among edge devices with privacy concern. The core of the FL strategy is the use of stochastic gradient descent (SGD) in a distributed manner. Large scale implementation of FL brings new challenges, such as the incorporation of acceleration techniques designed for SGD into the distributed setting, and mitigation of the drift problem due to non-homogeneous distribution of local datasets. These two problems have been separately studied in the literature; whereas, in this paper, we show that it is possible to address both problems using a single strategy without any major alteration to the FL framework, or introducing additional computation and communication load. To achieve this goal, we propose FedADC, which is an accelerated FL algorithm with drift control. We empirically illustrate the advantages of FedADC.

Coded computation can speed up distributed learning in the presence of straggling workers. Partial recovery of the gradient vector can further reduce the computation time at each iteration; however, this can result in biased estimators, which may slow down convergence, or even cause divergence. Estimator bias is particularly prevalent when the straggling behavior is correlated over time, which results in the gradient estimators being dominated by a few fast servers. To mitigate biased estimators, we design a timely dynamic encoding framework for partial recovery that includes an ordering operator that changes the codewords and computation orders at workers over time. To regulate the recovery frequencies, we adopt an age metric in the design of the dynamic encoding scheme. The proposed age-based scheme prioritizes the recovery of computations with relatively large age. We show through numerical results that the proposed dynamic encoding strategy increases the timeliness of the recovered computations, which, as a result, reduces the bias in model updates, and accelerates the convergence compared to conventional static partial recovery schemes.

We consider multiple devices with local datasets collaboratively learning a global model through device-to-device (D2D) communications. The conventional decentralized stochastic gradient descent (DSGD) solution for this problem assumes error-free orthogonal links among the devices. This is based on the assumption of an underlying communication protocol that takes care of the noise, fading, and interference in the wireless medium. In this work, we show the suboptimality of this approach by designing the communication and learning protocols jointly. We first consider a point-to-point (P2P) communication scheme by scheduling D2D transmissions in an orthogonal fashion to minimize interference. Then, we propose a novel over-the-air consensus scheme by exploiting the signal superposition property of wireless transmission, rather than avoiding interference. In the proposed OAC-MAC scheme, multiple nodes align their transmissions toward a single receiver node. For both schemes, we cast the scheduling problem as a graph coloring problem. We then numerically compare the two approaches for the distributed MNIST image classification task under various network conditions. We show that the OAC-MAC scheme attains better convergence speed and final accuracy thanks to the improved robustness against channel fading and noise. We also introduce a noise-aware version of the OAC-MAC scheme with further improvements in the convergence speed and accuracy.

We consider federated edge learning (FEEL), where mobile users (MUs) collaboratively learn a global model by sharing local updates on the model parameters rather than their datasets, with the help of a mobile base station (MBS). We optimize the resource allocation among MUs to reduce the communication latency in learning iterations. Observing that the performance in this centralized setting is limited due to the distance of the cell-edge users to the MBS, we introduce small cell base stations (SBSs) orchestrating FEEL among MUs within their cells, and periodically exchanging model updates with the MBS for global consensus. We show that this hierarchical federated learning (HFL) scheme significantly reduces the communication latency without sacrificing the accuracy.

We consider a cache-enabled heterogeneous cellular network, where mobile users (MUs) connect to multiple cache-enabled small-cell base stations (SBSs) during a video downloading session. SBSs can deliver these requests using their local cache contents as well as by downloading them from a macro-cell base station (MBS), which has access to the file library. We introduce a novel mobility-aware content storage and delivery scheme, which jointly exploits coded storage at the SBSs and coded delivery from the MBS to reduce the backhaul load from the MBS to the SBSs. We show that the proposed scheme provides a significant reduction both in the backhaul load when the cache capacity is sufficiently large, and in the number of sub-files required. Overall, for practical scenarios, in which the number of sub-files that can be created is limited either by the size of the files, or by the protocol overhead, the proposed coded caching and delivery scheme decidedly outperforms state-of-the-art alternatives. Finally, we show that the benefits of the proposed scheme also extends to scenarios with non-uniform file popularities and arbitrary mobility patterns.

Coded computation techniques provide robustness against straggling servers in distributed computing, with the following limitations: First, they increase decoding complexity. Second, they ignore computations carried out by straggling servers; and they are typically designed to recover the full gradient, and thus, cannot provide a balance between the accuracy of the gradient and per-iteration completion time. Here we introduce a hybrid approach, called coded partial gradient computation (CPGC), that benefits from the advantages of both coded and uncoded computation schemes, and reduces both the computation time and decoding complexity.

When gradient descent (GD) is scaled to many parallel computing servers (workers) for large scale machine learning problems, its per-iteration computation time is limited by the straggling workers. Coded distributed GD (DGD) can tolerate straggling workers by assigning redundant computations to the workers, but in most existing schemes, each non-straggling worker transmits one message per iteration to the parameter server (master) after completing all its computations. We allow multiple computations to be conveyed from each worker per iteration in order to exploit computations executed also by the straggling worker. We show that the average completion time per iteration can be reduced significantly at a reasonable increase in the communication load. We also propose a general coded DGD technique which can trade-off the average computation time with the communication load.

Proactive content caching at user devices and coded delivery is studied considering a non-uniform file popularity distribution. A novel centralized uncoded caching and coded delivery scheme, which can be applied to large file libraries, is proposed. The proposed cross-level coded delivery (CLCD) scheme is shown to achieve a lower average delivery rate than the state of art. In the proposed CLCD scheme, the same subpacketization is used for all the files in the library in order to prevent additional zero-padding in the delivery phase, and unlike the existing schemes in the literature, two users requesting files from different popularity groups can be served by the same multicast message in order to reduce the delivery rate. Simulation results indicate significant reduction in the average delivery rate for typical Zipf distribution parameter values.

Cache capacity-delay trade-off is studied for cooperative coded caching among small-cell base stations (SBSs) considering mobile users. First, a delay-aware coded caching policy is introduced, taking into account the popularity of the files and the maximum re-buffering delay constraint, which minimizes the average re-buffering delay of a mobile user under a given cache capacity constraint. Subsequently, a given average re-buffering delay constraint is considered to ensure a certain quality-of-service (QoS) target, and certain files are served by the macro-cell base station (MBS) when the cache capacity of the SBSs is not sufficient to store all the files in the library. A coded caching policy that minimizes the average amount of data served by the MBS is proposed for the latter scenario.

Playback delay control is an important mechanism to avoid jitter in video streaming systems. This paper introduces a playback delay minimization problem for multiuser video streaming systems providing a jitter-free video streaming service to end users in the system. In particular, a necessary condition on the playback delay for jitter-free streaming is obtained. Then, based on the derived necessary condition, an optimum rate splitting algorithm that splits available rate to all users is proposed. The proposed algorithm is optimum in the sense that it achieves the minimum system delay, which is defined as the maximum of all initial playback delays, while ensuring jitter-free streaming service to all users. Finally, using these results, an expression for the minimum system delay as a function of system parameters such as total rate and playback curves of requested video files is also derived.