Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks

Federated learning enables edge devices to collaboratively train a global model while maintaining data privacy by keeping data localized. However, the Non-IID nature of data distribution across devices often hinders model convergence and reduces performance. In this paper, we propose a novel plugin for federated optimization techniques that approximates Non-IID data distributions to IID through generative AI-enhanced data augmentation and balanced sampling strategy. Key idea is to synthesize additional data for underrepresented classes on each edge device, leveraging generative AI to create a more balanced dataset across the FL network. Additionally, a balanced sampling approach at the central server selectively includes only the most IID-like devices, accelerating convergence while maximizing the global model's performance. Experimental results validate that our approach significantly improves convergence speed and robustness against data imbalance, establishing a flexible, privacy-preserving FL plugin that is applicable even in data-scarce environments.

ROK Defense M&S in the Age of Hyperscale AI: Concepts, Challenges, and Future Directions

Integrating hyperscale AI into national defense modeling and simulation (M&S) is crucial for enhancing strategic and operational capabilities. We explore how hyperscale AI can revolutionize defense M\&S by providing unprecedented accuracy, speed, and the ability to simulate complex scenarios. Countries such as the United States and China are at the forefront of adopting these technologies and are experiencing varying degrees of success. Maximizing the potential of hyperscale AI necessitates addressing critical challenges, such as closed networks, long-tail data, complex decision-making, and a shortage of experts. Future directions emphasize the adoption of domestic foundation models, the investment in various GPUs / NPUs, the utilization of big tech services, and the use of open source software. These initiatives will enhance national security, maintain competitive advantages, and promote broader technological and economic progress. With this blueprint, the Republic of Korea can strengthen its defense capabilities and stay ahead of the emerging threats of modern warfare.

Reliable Sub-Nyquist Spectrum Sensing via Conformal Risk Control

Detecting occupied subbands is a key task for wireless applications such as unlicensed spectrum access. Recently, detection methods were proposed that extract per-subband features from sub-Nyquist baseband samples and then apply thresholding mechanisms based on held-out data. Such existing solutions can only provide guarantees in terms of false negative rate (FNR) in the asymptotic regime of large held-out data sets. In contrast, this work proposes a threshold mechanism-based conformal risk control (CRC), a method recently introduced in statistics. The proposed CRC-based thresholding technique formally meets user-specified FNR constraints, irrespective of the size of the held-out data set. By applying the proposed CRC-based framework to both reconstruction-based and classification-based sub-Nyquist spectrum sensing techniques, it is verified via experimental results that CRC not only provides theoretical guarantees on the FNR but also offers competitive true negative rate (TNR) performance.

RAQ-VAE: Rate-Adaptive Vector-Quantized Variational Autoencoder

Vector Quantized Variational AutoEncoder (VQ-VAE) is an established technique in machine learning for learning discrete representations across various modalities. However, its scalability and applicability are limited by the need to retrain the model to adjust the codebook for different data or model scales. We introduce the Rate-Adaptive VQ-VAE (RAQ-VAE) framework, which addresses this challenge with two novel codebook representation methods: a model-based approach using a clustering-based technique on an existing well-trained VQ-VAE model, and a data-driven approach utilizing a sequence-to-sequence (Seq2Seq) model for variable-rate codebook generation. Our experiments demonstrate that RAQ-VAE achieves effective reconstruction performance across multiple rates, often outperforming conventional fixed-rate VQ-VAE models. This work enhances the adaptability and performance of VQ-VAEs, with broad applications in data reconstruction, generation, and computer vision tasks.

On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction

Accurate uncertainty quantification in graph neural networks (GNNs) is essential, especially in high-stakes domains where GNNs are frequently employed. Conformal prediction (CP) offers a promising framework for quantifying uncertainty by providing $\textit{valid}$ prediction sets for any black-box model. CP ensures formal probabilistic guarantees that a prediction set contains a true label with a desired probability. However, the size of prediction sets, known as $\textit{inefficiency}$, is influenced by the underlying model and data generating process. On the other hand, Bayesian learning also provides a credible region based on the estimated posterior distribution, but this region is $\textit{well-calibrated}$ only when the model is correctly specified. Building on a recent work that introduced a scaling parameter for constructing valid credible regions from posterior estimate, our study explores the advantages of incorporating a temperature parameter into Bayesian GNNs within CP framework. We empirically demonstrate the existence of temperatures that result in more efficient prediction sets. Furthermore, we conduct an analysis to identify the factors contributing to inefficiency and offer valuable insights into the relationship between CP performance and model calibration.

FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients

Foundation models (FMs) have demonstrated remarkable performance in machine learning but demand extensive training data and computational resources. Federated learning (FL) addresses the challenges posed by FMs, especially related to data privacy and computational burdens. However, FL on FMs faces challenges in situations with heterogeneous clients possessing varying computing capabilities, as clients with limited capabilities may struggle to train the computationally intensive FMs. To address these challenges, we propose FedSplitX, a novel FL framework that tackles system heterogeneity. FedSplitX splits a large model into client-side and server-side components at multiple partition points to accommodate diverse client capabilities. This approach enables clients to collaborate while leveraging the server's computational power, leading to improved model performance compared to baselines that limit model size to meet the requirement of the poorest client. Furthermore, FedSplitX incorporates auxiliary networks at each partition point to reduce communication costs and delays while enhancing model performance. Our experiments demonstrate that FedSplitX effectively utilizes server capabilities to train large models, outperforming baseline approaches.

Cache-assisted Mobile Edge Computing over Space-Air-Ground Integrated Networks for Extended Reality Applications

Extended reality-enabled Internet of Things (XRI) provides the new user experience and the sense of immersion by adding virtual elements to the real world through Internet of Things (IoT) devices and emerging 6G technologies. However, the computational-intensive XRI tasks are challenging for the energy-constrained small-size XRI devices to cope with, and moreover certain data requires centralized computing that needs to be shared among users. To this end, we propose a cache-assisted space-air-ground integrated network mobile edge computing (SAGIN-MEC) system for XRI applications, consisting of two types of edge servers mounted on an unmanned aerial vehicle (UAV) and low Earth orbit (LEO) equipped with cache and the multiple ground XRI devices. For system efficiency, the four different offloading procedures of the XRI data are considered according to the type of information, i.e., shared data and private data, as well as the offloading decision and the caching status. Specifically, the private data can be offloaded to either UAV or LEO, while the offloading decision of the shared data to the LEO can be determined by the caching status. With the aim of maximizing the energy efficiency of the overall system, we jointly optimize UAV trajectory, resource allocation and offloading decisions under latency constraints and UAV's operational limitations by using the alternating optimization (AO)-based method along with Dinkelbach algorithm and successive convex optimization (SCA). Via numerical results, the proposed algorithm is verified to have the superior performance compared to conventional partial optimizations or without cache.

NeFL: Nested Federated Learning for Heterogeneous Clients

Federated learning (FL) is a promising approach in distributed learning keeping privacy. However, during the training pipeline of FL, slow or incapable clients (i.e., stragglers) slow down the total training time and degrade performance. System heterogeneity, including heterogeneous computing and network bandwidth, has been addressed to mitigate the impact of stragglers. Previous studies split models to tackle the issue, but with less degree-of-freedom in terms of model architecture. We propose nested federated learning (NeFL), a generalized framework that efficiently divides a model into submodels using both depthwise and widthwise scaling. NeFL is implemented by interpreting models as solving ordinary differential equations (ODEs) with adaptive step sizes. To address the inconsistency that arises when training multiple submodels with different architecture, we decouple a few parameters. NeFL enables resource-constrained clients to effectively join the FL pipeline and the model to be trained with a larger amount of data. Through a series of experiments, we demonstrate that NeFL leads to significant gains, especially for the worst-case submodel (e.g., 8.33 improvement on CIFAR-10). Furthermore, we demonstrate NeFL aligns with recent studies in FL.

Transceiver Design and Performance Analysis for LR-FHSS-based Direct-to-Satellite IoT

This paper presents a novel transceiver design aimed at enabling Direct-to-Satellite Internet of Things (DtS-IoT) systems based on long range-frequency hopping spread spectrum (LR-FHSS). Our focus lies in developing an accurate transmission method through the analysis of the frame structure and key parameters outlined in Long Range Wide-Area Network (LoRaWAN) [1]. To address the Doppler effect in DtS-IoT networks and simultaneously receive numerous frequency hopping signals, a robust signal detector for the receiver is proposed. We verify the performance of the proposed LR-FHSS transceiver design through simulations conducted in a realistic satellite channel environment, assessing metrics such as miss detection probability and packet error probability.

Energy-Efficient Vehicular Edge Computing with One-by-one Access Scheme

With the advent of ever-growing vehicular applications, vehicular edge computing (VEC) has been a promising solution to augment the computing capacity of future smart vehicles. The ultimate challenge to fulfill the quality of service (QoS) is increasingly prominent with constrained computing and communication resources of vehicles. In this paper, we propose an energy-efficient task offloading strategy for VEC system with one-by-one scheduling mechanism, where only one vehicle wakes up at a time to offload with a road side unit (RSU). The goal of system is to minimize the total energy consumption of vehicles by jointly optimizing user scheduling, offloading ratio and bit allocation within a given mission time. To this end, the non-convex and mixed-integer optimization problem is formulated and solved by adopting Lagrange dual problem, whose superior performances are verified via numerical results, as compared to other benchmark schemes.