PartialLoading: User Scheduling and Bandwidth Allocation for Parameter-sharing Edge Inference

By provisioning inference offloading services, edge inference drives the rapid growth of AI applications at the network edge. However, achieving high task throughput with stringent latency requirements remains a significant challenge. To address this issue, we develop a parameter-sharing AI model loading (PartialLoading) framework for multi-user edge inference, which exploits two key insights: 1) the majority of latency arises from loading AI models into server GPU memory, and 2) different AI models can share a significant number of parameters, for which redundant loading should be avoided. Towards this end, we formulate a joint multi-user scheduling and spectrum bandwidth allocation problem to maximize task throughput by exploiting shared parameter blocks across models. The intuition is to judiciously schedule user requests to reuse the shared parameter blocks between consecutively loaded models, thereby reducing model loading time substantially. To facilitate solution finding, we decouple the problem into two sub-problems, i.e., user scheduling and bandwidth allocation, showing that solving them sequentially is equivalent to solving the original problem. Due to the NP-hardness of the problem, we first study an important special case called the "bottom-layer-sharing" case, where AI models share some bottom layers within clusters, and design a dynamic programming-based algorithm to obtain the optimal solution in polynomial time. For the general case, where shared parameter blocks appear at arbitrary positions within AI models, we propose a greedy heuristic to obtain the sub-optimal solution efficiently. Simulation results demonstrate that the proposed framework significantly improves task throughput under deadline constraints compared with user scheduling without exploiting parameter sharing.

Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edge

The emergence of distributed Mixture-of-Experts (DMoE) systems, which deploy expert models at edge nodes, offers a pathway to achieving connected intelligence in sixth-generation (6G) mobile networks and edge artificial intelligence (AI). However, current DMoE systems lack an effective expert selection algorithm to address the simultaneous task-expert relevance and channel diversity inherent in these systems. Traditional AI or communication systems focus on either performance or channel conditions, and direct application of these methods leads to high communication overhead or low performance. To address this, we propose the DMoE protocol to schedule the expert inference and inter-expert transmission. This protocol identifies expert selection and subcarrier allocation as key optimization problems. We formulate an expert selection problem by incorporating both AI performance and channel conditions, and further extend it to a Joint Expert and Subcarrier Allocation (JESA) problem for comprehensive AI and channel management within the DMoE framework. For the NP-hard expert selection problem, we introduce the Dynamic Expert Selection (DES) algorithm, which leverages a linear relaxation as a bounding criterion to significantly reduce search complexity. For the JESA problem, we discover a unique structural property that ensures asymptotic optimality in most scenarios. We propose an iterative algorithm that addresses subcarrier allocation as a subproblem and integrates it with the DES algorithm. The proposed framework effectively manages the tradeoff between task relevance and channel conditions through a tunable importance factor, enabling flexible adaptation to diverse scenarios. Numerical experiments validate the dual benefits of the proposed expert selection algorithm: high performance and significantly reduced cost.

Semantic-Relevance Based Sensor Selection for Edge-AI Empowered Sensing Systems

The sixth-generation (6G) mobile network is envisioned to incorporate sensing and edge artificial intelligence (AI) as two key functions. Their natural convergence leads to the emergence of Integrated Sensing and Edge AI (ISEA), a novel paradigm enabling real-time acquisition and understanding of sensory information at the network edge. However, ISEA faces a communication bottleneck due to the large number of sensors and the high dimensionality of sensory features. Traditional approaches to communication-efficient ISEA lack awareness of semantic relevance, i.e., the level of relevance between sensor observations and the downstream task. To fill this gap, this paper presents a novel framework for semantic-relevance-aware sensor selection to achieve optimal end-to-end (E2E) task performance under heterogeneous sensor relevance and channel states. E2E sensing accuracy analysis is provided to characterize the sensing task performance in terms of selected sensors' relevance scores and channel states. Building on the results, the sensor-selection problem for accuracy maximization is formulated as an integer program and solved through a tight approximation of the objective. The optimal solution exhibits a priority-based structure, which ranks sensors based on a priority indicator combining relevance scores and channel states and selects top-ranked sensors. Low-complexity algorithms are then developed to determine the optimal numbers of selected sensors and features. Experimental results on both synthetic and real datasets show substantial accuracy gain achieved by the proposed selection scheme compared to existing benchmarks.

Ultra-Low-Latency Edge Intelligent Sensing: A Source-Channel Tradeoff and Its Application to Coding Rate Adaptation

The forthcoming sixth-generation (6G) mobile network is set to merge edge artificial intelligence (AI) and integrated sensing and communication (ISAC) extensively, giving rise to the new paradigm of edge intelligent sensing (EI-Sense). This paradigm leverages ubiquitous edge devices for environmental sensing and deploys AI algorithms at edge servers to interpret the observations via remote inference on wirelessly uploaded features. A significant challenge arises in designing EI-Sense systems for 6G mission-critical applications, which demand high performance under stringent latency constraints. To tackle this challenge, we focus on the end-to-end (E2E) performance of EI-Sense and characterize a source-channel tradeoff that balances source distortion and channel reliability. In this work, we establish a theoretical foundation for the source-channel tradeoff by quantifying the effects of source coding on feature discriminant gains and channel reliability on packet loss. Building on this foundation, we design the coding rate control by optimizing the tradeoff to minimize the E2E sensing error probability, leading to a low-complexity algorithm for ultra-low-latency EI-Sense. Finally, we validate our theoretical analysis and proposed coding rate control algorithm through extensive experiments on both synthetic and real datasets, demonstrating the sensing performance gain of our approach with respect to traditional reliability-centric methods.

Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

Integrated Sensing and Edge AI: Realizing Intelligent Perception in 6G

Sensing and edge artificial intelligence (AI) are envisioned as two essential and interconnected functions in sixth-generation (6G) mobile networks. On the one hand, sensing-empowered applications rely on powerful AI models to extract features and understand semantics from ubiquitous wireless sensors. On the other hand, the massive amount of sensory data serves as the fuel to continuously refine edge AI models. This deep integration of sensing and edge AI has given rise to a new task-oriented paradigm known as integrated sensing and edge AI (ISEA), which features a holistic design approach to communication, AI computation, and sensing for optimal sensing-task performance. In this article, we present a comprehensive survey for ISEA. We first provide technical preliminaries for sensing, edge AI, and new communication paradigms in ISEA. Then, we study several use cases of ISEA to demonstrate its practical relevance and introduce current standardization and industrial progress. Next, the design principles, metrics, tradeoffs, and architectures of ISEA are established, followed by a thorough overview of ISEA techniques, including digital air interface, over-the-air computation, and advanced signal processing. Its interplay with various 6G advancements, e.g., new physical-layer and networking techniques, are presented. Finally, we present future research opportunities in ISEA, including the integration of foundation models, convergence of ISEA and integrated sensing and communications (ISAC), and ultra-low-latency ISEA.

Communication Efficient Cooperative Edge AI via Event-Triggered Computation Offloading

Rare events, despite their infrequency, often carry critical information and require immediate attentions in mission-critical applications such as autonomous driving, healthcare, and industrial automation. The data-intensive nature of these tasks and their need for prompt responses, combined with designing edge AI (or edge inference), pose significant challenges in systems and techniques. Existing edge inference approaches often suffer from communication bottlenecks due to high-dimensional data transmission and fail to provide timely responses to rare events, limiting their effectiveness for mission-critical applications in the sixth-generation (6G) mobile networks. To overcome these challenges, we propose a channel-adaptive, event-triggered edge-inference framework that prioritizes efficient rare-event processing. Central to this framework is a dual-threshold, multi-exit architecture, which enables early local inference for rare events detected locally while offloading more complex rare events to edge servers for detailed classification. To further enhance the system's performance, we developed a channel-adaptive offloading policy paired with an online algorithm to dynamically determine the optimal confidence thresholds for controlling offloading decisions. The associated optimization problem is solved by reformulating the original non-convex function into an equivalent strongly convex one. Using deep neural network classifiers and real medical datasets, our experiments demonstrate that the proposed framework not only achieves superior rare-event classification accuracy, but also effectively reduces communication overhead, as opposed to existing edge-inference approaches.

Federated Dropout: Convergence Analysis and Resource Allocation

Federated Dropout is an efficient technique to overcome both communication and computation bottlenecks for deploying federated learning at the network edge. In each training round, an edge device only needs to update and transmit a sub-model, which is generated by the typical method of dropout in deep learning, and thus effectively reduces the per-round latency. \textcolor{blue}{However, the theoretical convergence analysis for Federated Dropout is still lacking in the literature, particularly regarding the quantitative influence of dropout rate on convergence}. To address this issue, by using the Taylor expansion method, we mathematically show that the gradient variance increases with a scaling factor of $\gamma/(1-\gamma)$, with $\gamma \in [0, \theta)$ denoting the dropout rate and $\theta$ being the maximum dropout rate ensuring the loss function reduction. Based on the above approximation, we provide the convergence analysis for Federated Dropout. Specifically, it is shown that a larger dropout rate of each device leads to a slower convergence rate. This provides a theoretical foundation for reducing the convergence latency by making a tradeoff between the per-round latency and the overall rounds till convergence. Moreover, a low-complexity algorithm is proposed to jointly optimize the dropout rate and the bandwidth allocation for minimizing the loss function in all rounds under a given per-round latency and limited network resources. Finally, numerical results are provided to verify the effectiveness of the proposed algorithm.

FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks

To bridge the digital divide, the space-ground integrated networks (SGINs), which will be a key component of the six-generation (6G) mobile networks, are expected to deliver artificial intelligence (AI) services to every corner of the world. One mission of SGINs is to support federated learning (FL) at a global scale. However, existing space-ground integrated FL frameworks involve ground stations or costly inter-satellite links, entailing excessive training latency and communication costs. To overcome these limitations, we propose an infrastructure-free federated learning framework based on a model dispersal (FedMeld) strategy, which exploits periodic movement patterns and store-carry-forward capabilities of satellites to enable parameter mixing across large-scale geographical regions. We theoretically show that FedMeld leads to global model convergence and quantify the effects of round interval and mixing ratio between adjacent areas on its learning performance. Based on the theoretical results, we formulate a joint optimization problem to design the staleness control and mixing ratio (SC-MR) for minimizing the training loss. By decomposing the problem into sequential SC and MR subproblems without compromising the optimality, we derive the round interval solution in a closed form and the mixing ratio in a semi-closed form to achieve the \textit{optimal} latency-accuracy tradeoff. Experiments using various datasets demonstrate that FedMeld achieves superior model accuracy while significantly reducing communication costs as compared with traditional FL schemes for SGINs.

LoLaFL: Low-Latency Federated Learning via Forward-only Propagation

Federated learning (FL) has emerged as a widely adopted paradigm for enabling edge learning with distributed data while ensuring data privacy. However, the traditional FL with deep neural networks trained via backpropagation can hardly meet the low-latency learning requirements in the sixth generation (6G) mobile networks. This challenge mainly arises from the high-dimensional model parameters to be transmitted and the numerous rounds of communication required for convergence due to the inherent randomness of the training process. To address this issue, we adopt the state-of-the-art principle of maximal coding rate reduction to learn linear discriminative features and extend the resultant white-box neural network into FL, yielding the novel framework of Low-Latency Federated Learning (LoLaFL) via forward-only propagation. LoLaFL enables layer-wise transmissions and aggregation with significantly fewer communication rounds, thereby considerably reducing latency. Additionally, we propose two \emph{nonlinear} aggregation schemes for LoLaFL. The first scheme is based on the proof that the optimal NN parameter aggregation in LoLaFL should be harmonic-mean-like. The second scheme further exploits the low-rank structures of the features and transmits the low-rank-approximated covariance matrices of features to achieve additional latency reduction. Theoretic analysis and experiments are conducted to evaluate the performance of LoLaFL. In comparison with traditional FL, the two nonlinear aggregation schemes for LoLaFL can achieve reductions in latency of over 91\% and 98\%, respectively, while maintaining comparable accuracies.