Wan Choi

Hyowoon Seo, Yoonseong Kang, Mehdi Bennis et al.

This work deals with the heterogeneous semantic-native communication (SNC) problem. When agents do not share the same communication context, the effectiveness of contextual reasoning (CR) is compromised calling for agents to infer other agents' context. This article proposes a novel framework for solving the inverse problem of CR in SNC using two Bayesian inference methods, namely: Bayesian inverse CR (iCR) and Bayesian inverse linearized CR (iLCR). The first proposed Bayesian iCR method utilizes Markov Chain Monte Carlo (MCMC) sampling to infer the agent's context while being computationally expensive. To address this issue, a Bayesian iLCR method is leveraged which obtains a linearized CR (LCR) model by training a linear neural network. Experimental results show that the Bayesian iLCR method requires less computation and achieves higher inference accuracy compared to Bayesian iCR. Additionally, heterogeneous SNC based on the context obtained through the Bayesian iLCR method shows better communication effectiveness than that of Bayesian iCR. Overall, this work provides valuable insights and methods to improve the effectiveness of SNC in situations where agents have different contexts.

Kwangjae Lee, Jung Hoon Lee, Wan Choi

In this paper, we introduce a novel approach to user-centric association and feedback bit allocation for the downlink of a cell-free massive MIMO (CF-mMIMO) system, operating under limited feedback constraints. In CF-mMIMO systems employing frequency division duplexing, each access point (AP) relies on channel information provided by its associated user equipments (UEs) for beamforming design. Since the uplink control channel is typically shared among UEs, we take account of each AP's total feedback budget, which is distributed among its associated UEs. By employing the Saleh-Valenzuela multi-resolvable path channel model with different average path gains, we first identify necessary feedback information for each UE, along with an appropriate codebook structure. This structure facilitates adaptive quantization of multiple paths based on their dominance. We then formulate a joint optimization problem addressing user-centric UE-AP association and feedback bit allocation. To address this challenge, we analyze the impact of feedback bit allocation and derive our proposed scheme from the solution of an alternative optimization problem aimed at devising long-term policies, explicitly considering the effects of feedback bit allocation. Numerical results show that our proposed scheme effectively enhances the performance of conventional approaches in CF-mMIMO systems.

Heekang Song, Wan Choi

We propose a communication-efficient optimally structured gradient coding scheme to jointly address straggler resilience and communication efficiency in heterogeneous distributed learning. By establishing a unified framework that simultaneously optimizes gradient coding and quantization, we formulate an optimization problem to minimize residual error subject to an unbiasedness constraint. We rigorously establish the joint global optimum by deriving a closed-form code structure coupled with an optimal bit allocation strategy, while simultaneously proposing a low-complexity bit allocation algorithm that efficiently yields near-optimal performance. We provide rigorous convergence analysis for convex and smooth functions. Experiments on the COCO dataset demonstrate that our joint design significantly accelerates convergence and enhances communication efficiency compared to existing baselines.

Bumjun Kim, Wan Choi

Transformer-based large language models (LLMs) have achieved remarkable success across various tasks. Yet, fine-tuning such massive models in federated learning (FL) settings poses significant challenges due to resource constraints and communication overhead. Low-Rank Adaptation (LoRA) addresses these issues by training compact, low-rank matrices instead of fully fine-tuning large models. This paper introduces a wireless federated LoRA fine-tuning framework that optimizes both learning performance and communication efficiency. We provide a novel convergence analysis, revealing how LoRA rank and covariance effects influence FL training dynamics. Leveraging these insights, we propose Sparsified Orthogonal Fine-Tuning (\textbf{SOFT}), an adaptive sparsification method that streamlines parameter updates without expensive matrix multiplications and singular value decomposition (SVD) operations. Additionally, we present a Two Stage Federated Algorithm (\textbf{TSFA}) algorithm that pre-determines key parameters offline and dynamically adjusts bandwidth and sparsification online, ensuring efficient training under latency constraints. Experiments on benchmark datasets show that our approach achieves accuracy comparable to ideal scenario models while significantly reducing communication overhead. Our framework thus enables scalable, resource-efficient deployment of large models in real-world wireless FL scenarios.

Heekang Song, Wan Choi

In this paper, we propose an optimally structured gradient coding scheme to mitigate the straggler problem in distributed learning. Conventional gradient coding methods often assume homogeneous straggler models or rely on excessive data replication, limiting performance in real-world heterogeneous systems. To address these limitations, we formulate an optimization problem minimizing residual error while ensuring unbiased gradient estimation by explicitly considering individual straggler probabilities. We derive closed-form solutions for optimal encoding and decoding coefficients via Lagrangian duality and convex optimization, and propose data allocation strategies that reduce both redundancy and computation load. We also analyze convergence behavior for $λ$-strongly convex and $μ$-smooth loss functions. Numerical results show that our approach significantly reduces the impact of stragglers and accelerates convergence compared to existing methods.

Hyowoon Seo, Jihong Park, Mehdi Bennis et al.

Designing distributed, fast and reliable wireless consensus protocols is instrumental in enabling mission-critical decentralized systems, such as robotic networks in the industrial Internet of Things (IIoT), drone swarms in rescue missions, and so forth. However, chasing both low-latency and reliability of consensus protocols is a challenging task. The problem is aggravated under wireless connectivity that may be slower and less reliable, compared to wired connections. To tackle this issue, we investigate fundamental relationships between consensus latency and reliability through the lens of wireless connectivity, and co-design communication and consensus protocols for low-latency and reliable decentralized systems. Specifically, we propose a novel communication-efficient distributed consensus protocol, termed Random Representative Consensus (R2C), and show its effectiveness under gossip and broadcast communication protocols. To this end, we derive a closed-form end-to-end (E2E) latency expression of the R2C that guarantees a target reliability, and compare it with a baseline consensus protocol, referred to as Referendum Consensus (RC). The result shows that the R2C is faster compared to the RC and more reliable compared when co-designed with the broadcast protocol compared to that with the gossip protocol.

Hyowoon Seo, Jihong Park, Mehdi Bennis et al.

This paper proposes Consensus-Before-Talk (CBT), a spectrum etiquette architecture leveraged by distributed ledger technology (DLT). In CBT, secondary users' spectrum access requests reach a consensus in a distributed way, thereby enabling collision-free distributed dynamic spectrum access. To achieve this consensus, the secondary users need to pay for the extra request exchanging delays. Incorporating the consensus delay, the end-to-end latency under CBT is investigated. Both the latency analysis and numerical evaluation validate that the proposed CBT achieves the lower end-to-end latency particularly under severe secondary user traffic, compared to the Listen-Before-Talk (LBT) benchmark scheme.