In wireless communication and edge computing networks, fractional programming (FP) and multiplicative programming (MP) are fundamental methodologies widely employed in solving non-convex optimization problems. Prior work introduced a remarkable method to solve non-convex functions with multiple ratios by deriving novel tight upper bounds, which we formalize as the UpperBound transform in this paper. However, the UpperBound transform faces critical limitations, particularly when directly extended to MP problems involving non-negative functions or discrete optimization variables. In this paper, we introduce a generalized transform termed the UP transform to overcome these limitations.We rigorously prove that the UP transform guarantees convergence to a Karush-Kuhn-Tucker (KKT) point for a broader class of MP problems, including scenarios where variables can be zero or discrete. We comprehensively illustrate the UP transform’s utility through two practical applications: partial task offloading in mobile edge computing, optimizing computation and energy efficiency; and user association coupled with resource allocation in heterogeneous networks, addressing mixed discrete-continuous optimization challenges. Comparative evaluations against conventional methods demonstrate superior convergence speed, efficiency, solution quality, and reduced computational complexity of the proposed UP transform based algorithms.

As mobile devices continue to drive advanced applications, edge computing has emerged as a crucial solution to overcome their inherent computational constraints, especially in deploying and training large language models (LLMs). Despite progress in edge computing, significant challenges remain in achieving efficient LLM training while addressing computational demands, energy consumption, and model stability. This paper presents an enhanced collaborative training framework that integrates mobile users with edge servers to optimize resource allocation. We extend the framework by incorporating model stability into the optimization objectives, mitigating performance instability often observed during distributed LLM fine-tuning. A multi-objective optimization problem is formulated to minimize energy consumption, delay, and instability, with a novel fractional programming technique and Iterative Rank Penalization (IRP) method proposed to improve the resource allocation and user-to-edge server associations. Compared to traditional methods like Semidefinite Relaxation, IRP achieves higher accuracy and computational efficiency. Extensive simulations demonstrate that our approach outperforms existing methods in reducing energy consumption and delay, and improving LLM stability across various mobile edge computing environments.

Federated Learning (FL) enables decentralized model training while preserving data privacy. Despite its benefits, FL faces challenges with non-identically distributed (non-IID) data, especially in long-tailed scenarios with imbalanced class samples. Momentum-based FL methods, often used to accelerate FL convergence, struggle with these distributions, resulting in biased models and making FL hard to converge. To understand this challenge, we conduct extensive investigations into this phenomenon, accompanied by a layer-wise analysis of neural network behavior. Based on these insights, we propose FedWCM, a method that dynamically adjusts momentum using global and per-round data to correct directional biases introduced by long-tailed distributions. Extensive experiments show that FedWCM resolves non-convergence issues and outperforms existing methods, enhancing FL’s efficiency and effectiveness in handling client heterogeneity and data imbalance.

In federated learning (FL), models must \emph{converge quickly} under tight communication budgets while \emph{generalizing} across non-IID client distributions. These twin requirements have naturally led to two widely used techniques: client/server \emph{momentum} to accelerate progress, and \emph{sharpness-aware minimization} (SAM) to prefer flat solutions. However, simply combining momentum and SAM leaves two structural issues unresolved in non-IID FL. We identify and formalize two failure modes: \emph{local–global curvature misalignment} (local SAM directions need not reflect the global loss geometry) and \emph{momentum-echo oscillation} (late-stage instability caused by accumulated momentum). To our knowledge, these failure modes have not been jointly articulated and addressed in the FL literature. We propose \textbf{FedWMSAM} to address both failure modes. First, we construct a momentum-guided global perturbation from server-aggregated momentum to align clients' SAM directions with the global descent geometry, enabling a \emph{single-backprop} SAM approximation that preserves efficiency. Second, we couple momentum and SAM via a cosine-similarity adaptive rule, yielding an early-momentum, late-SAM two-phase training schedule. We provide a non-IID convergence bound that \emph{explicitly models the perturbation-induced variance} $\sigma_\rho^2=\sigma^2+(L\rho)^2$ and its dependence on $(S,K,R,N)$ on the theory side. We conduct extensive experiments on multiple datasets and model architectures, and the results validate the effectiveness, adaptability, and robustness of our method, demonstrating its superiority in addressing the optimization challenges of Federated Learning. Our code is available at \url{https://github.com/Li-Tian-Le/NeurlPS_FedWMSAM}.

With the growing need for precise, context-aware Legal Information Retrieval (LIR) tools, this study explores the potential of Retrieval-Augmented Generation (RAG) for retrieving and synthesizing legal content. Using a dataset of legal documents spanning various legal sub-domains, we implement and evaluate the performance of various RAG configurations. By benchmarking each approach using precision and recall, we identify solutions that are suitable for professional deployment. Our results provide insight into how RAG addresses key challenges in legal information retrieval, such as mitigating hallucinations and improving the quality of results. By exploring different RAG techniques and their impact on performance, this research provides a pathway to integrate effective AI-driven solutions into professional legal environments.

The convergence of blockchain, Metaverse, and non-fungible tokens (NFTs) brings transformative digital opportunities alongside challenges like privacy and resource management. Addressing these, we focus on optimizing user connectivity and resource allocation in an NFT-centric and blockchain-enabled Metaverse in this paper. Through user work-offloading, we optimize data tasks, user connection parameters, and server computing frequency division. In the resource allocation phase, we optimize communication-computation resource distributions, including bandwidth, transmit power, and computing frequency. We introduce the trust-cost ratio (TCR), a pivotal measure combining trust scores from users’ resources and server history with delay and energy costs. This balance ensures sustained user engagement and trust. The DASHF algorithm, central to our approach, encapsulates the Dinkelbach algorithm, alternating optimization, semidefinite relaxation (SDR), the Hungarian method, and a novel fractional programming technique from a recent IEEE JSAC paper [2]. The most challenging part of DASHF is to rewrite an optimization problem as Quadratically Constrained Quadratic Programming (QCQP) via carefully designed transformations, in order to be solved by SDR and the Hungarian algorithm. Extensive simulations validate the DASHF algorithm’s efficacy, revealing critical insights for enhancing blockchain-Metaverse applications, especially with NFTs.

The Metaverse has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with the real world. Federated learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. Due to privacy concerns and the limited computation resources on mobile devices, we incorporate FL into MAR systems of the Metaverse to train a model cooperatively. Besides, to balance the trade-off between energy, execution latency and model accuracy, thereby accommodating different demands and application scenarios, we formulate an optimization problem to minimize a weighted combination of total energy consumption, completion time and model accuracy. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, CPU frequency and video frame resolution for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm has better performance (in terms of energy consumption, completion time and model accuracy) under different weight parameters compared to existing benchmarks.

The concept of the Metaverse has garnered growing interest from both academic and industry circles. The decentralization of both the integrity and security of digital items has spurred the popularity of play-to-earn (P2E) games, where players are entitled to earn and own digital assets which they may trade for physical-world currencies. However, these computationally-intensive games are hardly playable on resource-limited mobile devices and the computational tasks have to be offloaded to an edge server. Through mobile edge computing (MEC), users can upload data to the Metaverse Service Provider (MSP) edge servers for computing. Nevertheless, there is a trade-off between user-perceived in-game latency and user visual experience. The downlink transmission of lower-resolution videos lowers user-perceived latency while lowering the visual fidelity and consequently, earnings of users. In this paper, we design a method to enhance the Metaverse-based mobile augmented reality (MAR) in-game user experience. Specifically, we formulate and solve a multi-objective optimization problem. Given the inherent NP-hardness of the problem, we present a low-complexity algorithm to address it, mitigating the trade-off between delay and earnings. The experiment results show that our method can effectively balance the user-perceived latency and profitability, thus improving the performance of Metaverse-based MAR systems.

As mobile devices increasingly become focal points for advanced applications, edge computing presents a viable solution to their inherent computational limitations, particularly in deploying large language models (LLMs). However, despite the advancements in edge computing, significant challenges remain in efficient training and deploying LLMs due to the computational demands and data privacy concerns associated with these models. This paper explores a collaborative training framework that integrates mobile users with edge servers to optimize resource allocation, thereby enhancing both performance and efficiency. Our approach leverages parameter-efficient fine-tuning (PEFT) methods, allowing mobile users to adjust the initial layers of the LLM while edge servers handle the more demanding latter layers. Specifically, we formulate a multi-objective optimization problem to minimize the total energy consumption and delay during training. We also address the common issue of instability in model performance by incorporating stability enhancements into our objective function. Through novel fractional programming technique, we achieve a stationary point for the formulated problem. Simulations demonstrate that our method reduces the energy consumption as well as the latency, and increases the reliability of LLMs across various mobile settings.

In the upcoming 6G era, vehicular networks are shifting from simple Vehicle-to-Vehicle (V2V) communication to the more complex Vehicle-to-Everything (V2X) connectivity. At the forefront of this shift is the incorporation of Large Language Models (LLMs) into vehicles. Known for their sophisticated natural language processing abilities, LLMs change how users interact with their vehicles. This integration facilitates voice-driven commands and interactions, departing from the conventional manual control systems. However, integrating LLMs into vehicular systems presents notable challenges. The substantial computational demands and energy requirements of LLMs pose significant challenges, especially in the constrained environment of a vehicle. Additionally, the time-sensitive nature of tasks in vehicular networks adds another layer of complexity. In this paper, we consider an edge computing system where vehicles process the initial layers of LLM computations locally, and offload the remaining LLM computation tasks to the Roadside Units (RSUs), envisioning a vehicular ecosystem where LLM computations seamlessly interact with the ultra-low latency and high-bandwidth capabilities of 6G networks. To balance the trade-off between completion time and energy consumption, we formulate a multi-objective optimization problem to minimize the total cost of the vehicles and RSUs. The problem is then decomposed into two sub-problems, which are solved by sequential quadratic programming (SQP) method and fractional programming technique. The simulation results clearly indicate that the algorithm we have proposed is highly effective in reducing both the completion time and energy consumption of the system.

AI-Generated Content (AIGC), as a novel manner of providing Metaverse services in the forthcoming Internet paradigm, can resolve the obstacles of immersion requirements. Concurrently, edge computing, as an evolutionary paradigm of computing in communication systems, effectively augments real-time interactive services. In pursuit of enhancing the accessibility of AIGC services, the deployment of AIGC models (e.g., diffusion models) to edge servers and local devices has become a prevailing trend. Nevertheless, this approach faces constraints imposed by battery life and computational resources when tasks are offloaded to local devices, limiting the capacity to deliver high-quality content to users while adhering to stringent latency requirements. So there will be a tradeoff between the utility of AIGC models and offloading decisions in the edge computing paradigm. This paper presents a joint optimization scheme for offloading decisions, computation time, and diffusion steps of the diffusion models in the reverse diffusion stage. Moreover, we take the average error into consideration as the metric for evaluating the quality of the generated results. Experimental outcomes definitively show that the algorithm put forward outperforms baseline methods in terms of joint optimization performance.

Development of defenses against physical world attacks such as adversarial patches is gaining traction within the research community. We contribute to the field of adversarial patch detection by introducing an uncertainty-based adversarial patch localizer which localizes adversarial patch on an image, permitting post-processing patch-avoidance or patch-reconstruction. We quantify our prediction uncertainties with the development of Detection of Uncertainties in the Exceedance of Threshold (DUET) algorithm. This algorithm provides a framework to ascertain confidence in the adversarial patch localization, which is essential for safety-sensitive applications such as self-driving cars and medical imaging. We conducted experiments on localizing adversarial patches and found our proposed DUET model outperforms baseline models. We then conduct further analyses on our choice of model priors and the adoption of Bayesian Neural Networks in different layers within our model architecture. We found that isometric gaussian priors in Bayesian Neural Networks are suitable for patch localization tasks and the presence of Bayesian layers in the earlier neural network blocks facilitates top-end localization performance, while Bayesian layers added in the later neural network blocks contribute to better model generalization. We then propose two different well-performing models to tackle different use cases.

Federated Learning is a modern decentralized machine learning technique where user equipments perform machine learning tasks locally and then upload the model parameters to a central server. In this paper, we consider a 3-layer hierarchical federated learning system which involves model parameter exchanges between the cloud and edge servers, and the edge servers and user equipment. In a hierarchical federated learning model, delay in communication and computation of model parameters has a great impact on achieving a predefined global model accuracy. Therefore, we formulate a joint learning and communication optimization problem to minimize total model parameter communication and computation delay, by optimizing local iteration counts and edge iteration counts. To solve the problem, an iterative algorithm is proposed. After that, a time-minimized UE-to-edge association algorithm is presented where the maximum latency of the system is reduced. Simulation results show that the global model converges faster under optimal edge server and local iteration counts. The hierarchical federated learning latency is minimized with the proposed UE-to-edge association strategy.