Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions

Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets, enabling task-specific adaptation while preserving data privacy. However, fine-tuning the extensive parameters in LLMs is particularly challenging in resource-constrained federated scenarios due to the significant communication and computational costs. To gain a deeper understanding of how these challenges can be addressed, this article conducts a comparative analysis three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues: 1) FedLLMs, where clients upload model parameters or gradients to enable straightforward and effective fine-tuning; 2) KD-FedLLMs, which leverage KD for efficient knowledge sharing via logits; and 3) Split-FedLLMs, which split the LLMs into two parts, with one part executed on the client and the other one on the server, to balance the computational load. Each framework is evaluated based on key performance metrics, including model accuracy, communication overhead, and client-side computational load, offering insights into their effectiveness for various federated fine-tuning scenarios. Through this analysis, we identify framework-specific optimization opportunities to enhance the efficiency of FedLLMs and discuss broader research directions, highlighting open opportunities to better adapt FedLLMs for real-world applications. A use case is presented to demonstrate the performance comparison of these three frameworks under varying configurations and settings.

Optical Wireless Communications: Enabling the Next Generation Network of Networks

Optical wireless communication (OWC) is a promising technology anticipated to play a key role in the next-generation network of networks. To this end, this paper details the potential of OWC, as a complementary technology to traditional radio frequency communications, in enhancing networking capabilities beyond conventional terrestrial networks. Several usage scenarios and the current state of development are presented. Furthermore, a summary of existing challenges and opportunities are provided. Emerging technologies aimed at further enhancing future OWC capabilities are introduced. Additionally, value-added OWC-based technologies that leverage the unique properties of light are discussed, including applications such as positioning and gesture recognition. The paper concludes with the reflection that OWC provides unique functionalities that can play a crucial role in building convergent and resilient future network of networks.

Antenna Activation for NOMA Assisted Pinching-Antenna Systems

In this letter, a non-orthogonal multiple access (NOMA) assisted downlink pinching-antenna system is investigated, where multiple pinching antennas can be activated at pre-configured positions along a dielectric waveguide to serve users via NOMA. In particular, the objective of this letter is to study at what locations and how many pinching antennas should be activated in order to maximize the system throughput. To this end, a sum rate maximization problem with antenna activation is formulated. With the help of matching theory, the formulated problem can be recast as a one-sided one-to-one matching, for which a low-complexity algorithm is developed. Simulation results indicate that the considered NOMA assisted pinching-antenna system can outperform conventional fixed-antenna systems in terms of sum rate, and the proposed matching based antenna activation algorithm yields a significant performance gain over the considered benchmarks.

Flexible-Antenna Systems: A Pinching-Antenna Perspective

Flexible-antenna systems have recently received significant research interest due to their capability to reconfigure wireless channels intelligently. This paper focuses on a new type of flexible-antenna technology, termed pinching antennas, which can be realized by applying small dielectric particles on a waveguide. Analytical results are first developed for the simple case with a single pinching antenna and a single waveguide, where the unique feature of the pinching-antenna system to create strong line-of-sight links and mitigate large-scale path loss is demonstrated. An advantageous feature of pinching-antenna systems is that multiple pinching antennas can be activated on a single waveguide at no extra cost; however, they must be fed with the same signal. This feature motivates the application of non-orthogonal multiple access (NOMA), and analytical results are provided to demonstrate the superior performance of NOMA-assisted pinching-antenna systems. Finally, the case with multiple pinching antennas and multiple waveguides is studied, which resembles a classical multiple-input single-input (MISO) interference channel. By exploiting the capability of pinching antennas to reconfigure the wireless channel, it is revealed that a performance upper bound on the interference channel becomes achievable, where the achievability conditions are also identified. Computer simulation results are presented to verify the developed analytical results and demonstrate the superior performance of pinching-antenna systems.

Rate Splitting Multiple Access for RIS-aided URLLC MIMO Broadcast Channels

The performance of modern wireless communication systems is typically limited by interference. The impact of interference can be even more severe in ultra-reliable and low-latency communication (URLLC) use cases. A powerful tool for managing interference is rate splitting multiple access (RSMA), which encompasses many multiple-access technologies like non-orthogonal multiple access (NOMA), spatial division multiple access (SDMA), and broadcasting. Another effective technology to enhance the performance of URLLC systems and mitigate interference is constituted by reconfigurable intelligent surfaces (RISs). This paper develops RSMA schemes for multi-user multiple-input multiple-output (MIMO) RIS-aided broadcast channels (BCs) based on finite block length (FBL) coding. We show that RSMA and RISs can substantially improve the spectral efficiency (SE) and energy efficiency (EE) of MIMO RIS-aided URLLC systems. Additionally, the gain of employing RSMA and RISs noticeably increases when the reliability and latency constraints are more stringent. Furthermore, RISs impact RSMA differently, depending on the user load. If the system is underloaded, RISs are able to manage the interference sufficiently well, making the gains of RSMA small. However, when the user load is high, RISs and RSMA become synergetic.

Sensing Accuracy Optimization for Communication-assisted Dual-baseline UAV-InSAR

In this paper, we study the optimization of the sensing accuracy of unmanned aerial vehicle (UAV)-based dual-baseline interferometric synthetic aperture radar (InSAR) systems. A swarm of three UAV-synthetic aperture radar (SAR) systems is deployed to image an area of interest from different angles, enabling the creation of two independent digital elevation models (DEMs). To reduce the InSAR sensing error, i.e., the height estimation error, the two DEMs are fused based on weighted average techniques into one final DEM. The heavy computations required for this process are performed on the ground. To this end, the radar data is offloaded in real time via a frequency division multiple access (FDMA) air-to-ground backhaul link. In this work, we focus on improving the sensing accuracy by minimizing the worst-case height estimation error of the final DEM. To this end, the UAV formation and the power allocated for offloading are jointly optimized based on alternating optimization (AO), while meeting practical InSAR sensing and communication constraints. Our simulation results demonstrate that the proposed solution can improve the sensing accuracy by over 39% compared to a classical single-baseline UAV-InSAR system and by more than 12% compared to other benchmark schemes.

Molecular Signal Reception in Complex Vessel Networks: The Role of the Network Topology

The notion of synthetic molecular communication (MC) refers to the transmission of information via molecules and is largely foreseen for use within the human body, where traditional electromagnetic wave (EM)-based communication is impractical. MC is anticipated to enable innovative medical applications, such as early-stage tumor detection, targeted drug delivery, and holistic approaches like the Internet of Bio-Nano Things (IoBNT). Many of these applications involve parts of the human cardiovascular system (CVS), here referred to as networks, posing challenges for MC due to their complex, highly branched vessel structures. To gain a better understanding of how the topology of such branched vessel networks affects the reception of a molecular signal at a target location, e.g., the network outlet, we present a generic analytical end-to-end model that characterizes molecule propagation and reception in linear branched vessel networks (LBVNs). We specialize this generic model to any MC system employing superparamagnetic iron-oxide nanoparticles (SPIONs) as signaling molecules and a planar coil as receiver (RX). By considering components that have been previously established in testbeds, we effectively isolate the impact of the network topology and validate our theoretical model with testbed data. Additionally, we propose two metrics, namely the molecule delay and the multi-path spread, that relate the LBVN topology to the molecule dispersion induced by the network, thereby linking the network structure to the signal-to-noise ratio (SNR) at the target location. This allows the characterization of the SNR at any point in the network solely based on the network topology. Consequently, our framework can, e.g., be exploited for optimal sensor placement in the CVS or identification of suitable testbed topologies for given SNR requirements.

Two Birds With One Stone: Enhancing Communication and Sensing via Multi-Functional RIS

In this article, we propose new network architectures that integrate multi-functional reconfigurable intelligent surfaces (MF-RISs) into 6G networks to enhance both communication and sensing capabilities. Firstly, we elaborate how to leverage MF-RISs for improving communication performance in different communication modes including unicast, mulitcast, and broadcast and for different multi-access schemes. Next, we emphasize synergistic benefits of integrating MF-RISs with wireless sensing, enabling more accurate and efficient target detection in 6G networks. Furthermore, we present two schemes that utilize MF-RISs to enhance the performance of integrated sensing and communication (ISAC). We also study multi-objective optimization to achieve the optimal trade-off between communication and sensing performance. Finally, we present numerical results to show the performance improvements offered by MF-RISs compared to conventional RISs in ISAC. We also outline key research directions for MF-RIS under the ambition of 6G.

Near-Field Multipath MIMO Channel Model for Imperfect Surface Reflection

Near-field (NF) communications is receiving renewed attention in the context of passive reconfigurable intelligent surfaces (RISs) due to their potentially extremely large dimensions. Although line-of-sight (LOS) links are expected to be dominant in NF scenarios, it is not a priori obvious whether or not the impact of non-LOS components can be neglected. Furthermore, despite being weaker than the LOS link, non-LOS links may be required to achieve multiplexing gains in multi-user multiple-input multiple-output (MIMO) scenarios. In this paper, we develop a generalized statistical NF model for RIS-assisted MIMO systems that extends the widely adopted point-scattering model to account for imperfect reflections at large surfaces like walls, ceilings, and the ground. Our simulation results confirm the accuracy of the proposed model and reveal that in various practical scenarios, the impact of non-LOS components is indeed non-negligible, and thus, needs to be carefully taken into consideration.

Distributed Channel Estimation for 6D Movable Antenna: Unveiling Directional Sparsity

Six-dimensional movable antenna (6DMA) is an innovative technology to improve wireless network capacity by adjusting 3D positions and 3D rotations of antenna surfaces based on channel spatial distribution. However, the existing works on 6DMA have assumed a central processing unit (CPU) to jointly process the signals of all 6DMA surfaces to execute various tasks. This inevitably incurs prohibitively high processing cost for channel estimation. Therefore, we propose a distributed 6DMA processing architecture to reduce processing complexity of CPU by equipping each 6DMA surface with a local processing unit (LPU). In particular, we unveil for the first time a new \textbf{\textit{directional sparsity}} property of 6DMA channels, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs, which can receive direct/reflected signals from users. In addition, we propose a practical three-stage protocol for the 6DMA-equipped base station (BS) to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization, and instantaneous channel estimation for user data transmission with optimized 6DMA positions/rotations. Specifically, the directional sparsity is leveraged to develop distributed algorithms for joint sparsity detection and channel power estimation, as well as for directional sparsity-aided instantaneous channel estimation. Using the estimated channel power, we develop a channel power-based optimization algorithm to maximize the ergodic sum rate of the users by optimizing the antenna positions/rotations. Simulation results show that our channel estimation algorithms are more accurate than benchmarks with lower pilot overhead, and our optimization outperforms fluid/movable antennas optimized only in two dimensions (2D), even when the latter have perfect instantaneous CSI.