arXiv subjects

Liping Qian

Publications and source records attributed to Liping Qian.

10 recordsLinked to original sources

arXiv2026

Joint Source-Channel-Check Coding with HARQ for Reliable Semantic Communications

Semantic communication has emerged as a promising paradigm for improving transmission efficiency and task-level reliability, yet most existing reliability-enhancement approaches rely on retransmission strategies driven by semantic fidelity checking that require additional check codewords solely for retransmission triggering, thereby incurring substantial communication overhead. In this paper, we propose S3CHARQ, a Joint Source-Channel-Check Coding framework with hybrid automatic repeat request that fundamentally rethinks the role of check codewords in semantic communications. By integrating the check codeword into the JSCC process, S3CHARQ enables JS3C, allowing the check codeword to simultaneously support semantic fidelity verification and reconstruction enhancement. At the transmitter, a semantic fidelity-aware check encoder embeds auxiliary reconstruction information into the check codeword. At the receiver, the JSCC and check codewords are jointly decoded by a JS3C decoder, while the check codeword is additionally exploited for perceptual quality estimation. Moreover, because retransmission decisions are necessarily based on imperfect semantic quality estimation in the absence of ground-truth reconstruction, estimation errors are unavoidable and fundamentally limit the effectiveness of rule-based decision schemes. To overcome this limitation, we develop a reinforcement learning-based retransmission decision module that enables adaptive, sample-level retransmission decisions, effectively balancing recovery and refinement information under dynamic channel conditions. Experimental results demonstrate that compared with existing HARQ-based semantic communication systems, the proposed S3CHARQ framework achieves a 2.36 dB improvement in the 97th percentile PSNR, as well as a 37.45% reduction in outage probability.

eess.IV↗

arXiv2026

Toward Resource-Efficient Collaboration of Large AI Models in Mobile Edge Networks

The collaboration of large artificial intelligence (AI) models in mobile edge networks has emerged as a promising paradigm to meet the growing demand for intelligent services at the network edge. By enabling multiple devices to cooperatively execute submodels or subtasks, collaborative AI enhances inference efficiency and service quality with constrained resources. However, deploying large AI models in such environments remains challenging due to the intrinsic mismatch between model complexity and the limited computation, memory, and communication resources in edge networks. This article provides a comprehensive overview of the system architecture for collaborative AI in mobile edge networks, along with representative application scenarios in transportation and healthcare. We further present recent advances in resource-efficient collaboration techniques, categorized into spatial and temporal approaches. The major spatial approaches include federated tuning, mixture of experts, patch-based diffusion, and hierarchical diffusion. Meanwhile, the important temporal approaches encompass split learning, cascading inference, speculative decoding, and routing inference. Building upon these foundations, we propose a multi-stage diffusion framework that enables elastic distribution of large generative models across heterogeneous edge resources. Experimental results demonstrate that our framework achieves performance improvement in both efficiency and adaptability for data generation.

cs.NI↗

arXiv2025

Adaptive AI Agent Placement and Migration in Edge Intelligence Systems

The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud data centers, traditionally used for agent deployment, introduces significant latency. Deploying AI agents at the edge improves efficiency and reduces latency. However, edge environments present challenges due to limited and heterogeneous resources. Maintaining QoS for mobile users necessitates agent migration, which is complicated by the complexity of AI agents coordinating LLMs, task planning, memory, and external tools. This paper presents the first systematic deployment and management solution for LLM-based AI agents in dynamic edge environments. We propose a novel adaptive framework for AI agent placement and migration in edge intelligence systems. Our approach models resource constraints and latency/cost, leveraging ant colony algorithms and LLM-based optimization for efficient decision-making. It autonomously places agents to optimize resource utilization and QoS and enables lightweight agent migration by transferring only essential state. Implemented on a distributed system using AgentScope and validated across globally distributed edge servers, our solution significantly reduces deployment latency and migration costs.

cs.AI↗

arXiv2025

Scalable Multi-task Edge Sensing via Task-oriented Joint Information Gathering and Broadcast

The recent advance of edge computing technology enables significant sensing performance improvement of Internet of Things (IoT) networks. In particular, an edge server (ES) is responsible for gathering sensing data from distributed sensing devices, and immediately executing different sensing tasks to accommodate the heterogeneous service demands of mobile users. However, as the number of users surges and the sensing tasks become increasingly compute-intensive, the huge amount of computation workloads and data transmissions may overwhelm the edge system of limited resources. Accordingly, we propose in this paper a scalable edge sensing framework for multi-task execution, in the sense that the computation workload and communication overhead of the ES do not increase with the number of downstream users or tasks. By exploiting the task-relevant correlations, the proposed scheme implements a unified encoder at the ES, which produces a common low-dimensional message from the sensing data and broadcasts it to all users to execute their individual tasks. To achieve high sensing accuracy, we extend the well-known information bottleneck theory to a multi-task scenario to jointly optimize the information gathering and broadcast processes. We also develop an efficient two-step training procedure to optimize the parameters of the neural network-based codecs deployed in the edge sensing system. Experiment results show that the proposed scheme significantly outperforms the considered representative benchmark methods in multi-task inference accuracy. Besides, the proposed scheme is scalable to the network size, which maintains almost constant computation delay with less than 1% degradation of inference performance when the user number increases by four times.

eess.SP↗

arXiv2024

Digital Semantic Communications: An Alternating Multi-Phase Training Strategy with Mask Attack

Semantic communication (SemComm) has emerged as new paradigm shifts.Most existing SemComm systems transmit continuously distributed signals in analog fashion.However, the analog paradigm is not compatible with current digital communication frameworks. In this paper, we propose an alternating multi-phase training strategy (AMP) to enable the joint training of the networks in the encoder and decoder through non-differentiable digital processes. AMP contains three training phases, aiming at feature extraction (FE), robustness enhancement (RE), and training-testing alignment (TTA), respectively. AMP contains three training phases, aiming at feature extraction (FE), robustness enhancement (RE), and training-testing alignment (TTA), respectively. In particular, in the FE stage, we learn the representation ability of semantic information by end-to-end training the encoder and decoder in an analog manner. When we take digital communication into consideration, the domain shift between digital and analog demands the fine-tuning for encoder and decoder. To cope with joint training process within the non-differentiable digital processes, we propose the alternation between updating the decoder individually and jointly training the codec in RE phase. To boost robustness further, we investigate a mask-attack (MATK) in RE to simulate an evident and severe bit-flipping effect in a differentiable manner. To address the training-testing inconsistency introduced by MATK, we employ an additional TTA phase, fine-tuning the decoder without MATK. Combining with AMP and an information restoration network, we propose a digital SemComm system for image transmission, named AMP-SC. Comparing with the representative benchmark, AMP-SC achieves $0.82 \sim 1.65$dB higher average reconstruction performance among various representative datasets at different scales and a wide range of signal-to-noise ratio.

eess.SP↗

arXiv2023

Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices

Distributed Artificial Intelligence (AI) model training over mobile edge networks encounters significant challenges due to the data and resource heterogeneity of edge devices. The former hampers the convergence rate of the global model, while the latter diminishes the devices' resource utilization efficiency. In this paper, we propose a generative AI-empowered federated learning to address these challenges by leveraging the idea of FIlling the MIssing (FIMI) portion of local data. Specifically, FIMI can be considered as a resource-aware data augmentation method that effectively mitigates the data heterogeneity while ensuring efficient FL training. We first quantify the relationship between the training data amount and the learning performance. We then study the FIMI optimization problem with the objective of minimizing the device-side overall energy consumption subject to required learning performance constraints. The decomposition-based analysis and the cross-entropy searching method are leveraged to derive the solution, where each device is assigned suitable AI-synthesized data and resource utilization policy. Experiment results demonstrate that FIMI can save up to 50% of the device-side energy to achieve the target global test accuracy in comparison with the existing methods. Meanwhile, FIMI can significantly enhance the converged global accuracy under the non-independently-and-identically distribution (non-IID) data.

cs.LG↗

arXiv2023

FAST: Fidelity-Adjustable Semantic Transmission over Heterogeneous Wireless Networks

In this work, we investigate the challenging problem of on-demand semantic communication over heterogeneous wireless networks. We propose a fidelity-adjustable semantic transmission framework (FAST) that empowers wireless devices to send data efficiently under different application scenarios and resource conditions. To this end, we first design a dynamic sub-model training scheme to learn the flexible semantic model, which enables edge devices to customize the transmission fidelity with different widths of the semantic model. After that, we focus on the FAST optimization problem to minimize the system energy consumption with latency and fidelity constraints. Following that, the optimal transmission strategies including the scaling factor of the semantic model, computing frequency, and transmitting power are derived for the devices. Experiment results indicate that, when compared to the baseline transmission schemes, the proposed framework can reduce up to one order of magnitude of the system energy consumption and data size for maintaining reasonable data fidelity.

cs.NI↗

arXiv2015

Joint Scheduling and Power Allocations for Traffic Offloading via Dual-Connectivity

With the rapid growth of mobile traffic demand, a promising approach to relieve cellular network congestion is to offload users' traffic to small-cell networks. In this paper, we investigate how the mobile users (MUs) can effectively offload traffic by taking advantage of the capability of dual-connectivity, which enables an MU to simultaneously communicate with a macro base station (BS) and a small-cell access point (AP) via two radio-interfaces. Offloading traffic to the AP usually reduces the MUs' mobile data cost, but often at the expense of suffering increased interferences from other MUs at the same AP. We thus formulate an optimization problem that jointly determines each MU's traffic schedule (between the BS and AP) and power control (between two radio-interfaces). The system objective is to minimize all MUs' total cost, while satisfying each MU's transmit-power constraints through proper interference control. In spite of the non-convexity of the problem, we design both a centralized algorithm and a distributed algorithm to solve the joint optimization problem. Numerical results show that the proposed algorithms can achieve the close-to-optimum results comparing with the ones achieved by the LINGO (a commercial optimization software), but with significantly less computational complexity. The results also show that the proposed adaptive offloading can significantly reduce the MUs' cost, i.e., save more than 75% of the cost without offloading traffic and 65% of the cost with a fixed offloading.

cs.NI↗

arXiv2012

Energy-Efficient Delay-Constrained Transmission and Sensing for Cognitive Radio Systems

In this work we study energy-efficient transmission for Cognitive Radio (CR) which opportunistically operates on Primary User's (PU's) channel through spectrum sensing. Spectrum sensing and compulsory idling (for incumbent protection) introduce energy-overheads for Secondary User's (SU's) operations, and thus an appropriate balance between energy consumption in data transmission and energy-overheads is required. We formulate this problem as a discrete-time Markov Decision Process (MDP) in which the SU aims at minimizing its average cost (including both energy consumption and delay cost) to finish a target traffic payload through an appropriate rate allocation. Based on Certainty Equivalent Control, we propose a low-complexity rate-adaptation policy that achieves comparable performance as the optimal policy. With the low-complexity policy, we quantify the impact of energy-overheads (including the power consumption for spectrum sensing and compulsory idling) on the SU transmission strategy. Specifically, the SU rate increases with the increase of energy-overheads, whose marginal impact, however, diminishes. Moreover, the marginal impact of energy-overheads is more significant for delay-insensitive traffic compared to that for delay-sensitive traffic. To mitigate the loss due to imperfect spectrum sensing, we quantify that the SU decreases (increases) its rate with a larger mis-detection probability (false alarm probability).

cs.NI↗

arXiv2008

MAPEL: Achieving Global Optimality for a Non-convex Wireless Power Control Problem

Achieving weighted throughput maximization (WTM) through power control has been a long standing open problem in interference-limited wireless networks. The complicated coupling between the mutual interferences of links gives rise to a non-convex optimization problem. Previous work has considered the WTM problem in the high signal to interference-and-noise ratio (SINR) regime, where the problem can be approximated and transformed into a convex optimization problem through proper change of variables. In the general SINR regime, however, the approximation and transformation approach does not work. This paper proposes an algorithm, MAPEL, which globally converges to a global optimal solution of the WTM problem in the general SINR regime. The MAPEL algorithm is designed based on three key observations of the WTM problem: (1) the objective function is monotonically increasing in SINR, (2) the objective function can be transformed into a product of exponentiated linear fraction functions, and (3) the feasible set of the equivalent transformed problem is always normal although not necessarily convex. The MAPLE algorithm finds the desired optimal power control solution by constructing a series of polyblocks that approximate the feasible SINR region in increasing precision. Furthermore, by tuning the approximation factor in MAPEL, we could engineer a desirable tradeoff between optimality and convergence time. MAPEL provides an important benchmark for performance evaluation of other heuristic algorithms targeting the same problem. With the help of MAPEL, we evaluate the performance of several respective algorithms through extensive simulations.

cs.NI↗