arXiv subjects

Di Yuan

Publications and source records attributed to Di Yuan.

At least 19 recordsLinked to original sources

arXiv2026

Optimal Routing for Federated Learning over Dynamic Satellite Networks: Tractable or Not?

Federated learning (FL) is a key paradigm for distributed model learning across decentralized data sources. Communication in each FL round typically consists of two phases: (i) distributing the global model from a server to clients, and (ii) collecting updated local models from clients to the server for aggregation. This paper focuses on a type of FL where communication between a client and the server is relay-based over dynamic networks, making routing optimization essential. A typical scenario is in-orbit FL, where satellites act as clients and communicate with a server (which can be a satellite, ground station, or aerial platform) via multi-hop inter-satellite links. This paper presents a comprehensive tractability analysis of routing optimization for in-orbit FL under different settings. For global model distribution, these include the number of models, the objective function, and routing schemes (unicast versus multicast, and splittable versus unsplittable flow). For local model collection, the settings consider the number of models, client selection, and flow splittability. For each case, we rigorously prove whether the global optimum is obtainable in polynomial time or the problem is NP-hard. Together, our analysis draws clear boundaries between tractable and intractable regimes for a broad spectrum of routing problems for in-orbit FL. For tractable cases, the derived efficient algorithms are directly applicable in practice. For intractable cases, we provide fundamental insights into their inherent complexity. These contributions fill a critical yet unexplored research gap, laying a foundation for principled routing design, evaluation, and deployment in satellite-based FL or similar distributed learning systems.

cs.LG↗

arXiv2025

FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference due to the complex sampling trajectories from noise to image. To address this, we formulate image fusion as a direct probabilistic transport from source modalities to the fused image distribution, leveraging the flow matching paradigm to improve sampling efficiency and structural consistency. To mitigate the lack of high-quality fused images for supervision, we collect fusion results from multiple state-of-the-art models as priors, and employ a task-aware selection function to select the most reliable pseudo-labels for each task. We further introduce a Fusion Refiner module that employs a divide-and-conquer strategy to systematically identify, decompose, and enhance degraded components in selected pseudo-labels. For multi-task scenarios, we integrate elastic weight consolidation and experience replay mechanisms to preserve cross-task performance and enhance continual learning ability from both parameter stability and memory retention perspectives. Our approach achieves competitive performance across diverse fusion tasks, while significantly improving sampling efficiency and maintaining a lightweight model design. The code will be available at: https://github.com/Ist-Zhy/FusionFM.

cs.CV↗

arXiv2025

Forecasting Spoken Language Development in Children with Cochlear Implants Using Preimplantation MRI

Cochlear implants (CI) significantly improve spoken language in children with severe-to-profound sensorineural hearing loss (SNHL), yet outcomes remain more variable than in children with normal hearing. This variability cannot be reliably predicted for individual children using age at implantation or residual hearing. This study aims to compare the accuracy of traditional machine learning (ML) to deep transfer learning (DTL) algorithms to predict post-CI spoken language development of children with bilateral SNHL using a binary classification model of high versus low language improvers. A total of 278 implanted children enrolled from three centers. The accuracy, sensitivity and specificity of prediction models based upon brain neuroanatomic features using traditional ML and DTL learning. DTL prediction models using bilinear attention-based fusion strategy achieved: accuracy of 92.39% (95% CI, 90.70%-94.07%), sensitivity of 91.22% (95% CI, 89.98%-92.47%), specificity of 93.56% (95% CI, 90.91%-96.21%), and area under the curve (AUC) of 0.977 (95% CI, 0.969-0.986). DTL outperformed traditional ML models in all outcome measures. DTL was significantly improved by direct capture of discriminative and task-specific information that are advantages of representation learning enabled by this approach over ML. The results support the feasibility of a single DTL prediction model for language prediction of children served by CI programs worldwide.

cs.CL↗

arXiv2025

Mobility-Aware Multi-Task Decentralized Federated Learning for Vehicular Networks: Modeling, Analysis, and Optimization

Federated learning (FL) is a promising paradigm that can enable collaborative model training between vehicles while protecting data privacy, thereby significantly improving the performance of intelligent transportation systems (ITSs). In vehicular networks, due to mobility, resource constraints, and the concurrent execution of multiple training tasks, how to allocate limited resources effectively to achieve optimal model training of multiple tasks is an extremely challenging issue. In this paper, we propose a mobility-aware multi-task decentralized federated learning (MMFL) framework for vehicular networks. By this framework, we address task scheduling, subcarrier allocation, and leader selection, as a joint optimization problem, termed as TSLP. For the case with a single FL task, we derive the convergence bound of model training. For general cases, we first model TSLP as a resource allocation game, and prove the existence of a Nash equilibrium (NE). Then, based on this proof, we reformulate the game as a decentralized partially observable Markov decision process (DEC-POMDP), and develop an algorithm based on heterogeneous-agent proximal policy optimization (HAPPO) to solve DEC-POMDP. Finally, numerical results are used to demonstrate the effectiveness of the proposed algorithm.

cs.NI↗

arXiv2025

WECAR: An End-Edge Collaborative Inference and Training Framework for WiFi-Based Continuous Human Activity Recognition

WiFi-based human activity recognition (HAR) holds significant promise for ubiquitous sensing in smart environments. A critical challenge lies in enabling systems to dynamically adapt to evolving scenarios, learning new activities without catastrophic forgetting of prior knowledge, while adhering to the stringent computational constraints of edge devices. Current approaches struggle to reconcile these requirements due to prohibitive storage demands for retaining historical data and inefficient parameter utilization. We propose WECAR, an end-edge collaborative inference and training framework for WiFi-based continuous HAR, which decouples computational workloads to overcome these limitations. In this framework, edge devices handle model training, lightweight optimization, and updates, while end devices perform efficient inference. WECAR introduces two key innovations, i.e., dynamic continual learning with parameter efficiency and hierarchical distillation for end deployment. For the former, we propose a transformer-based architecture enhanced by task-specific dynamic model expansion and stability-aware selective retraining. For the latter, we propose a dual-phase distillation mechanism that includes multi-head self-attention relation distillation and prefix relation distillation. We implement WECAR based on heterogeneous hardware using Jetson Nano as edge devices and the ESP32 as end devices, respectively. Our experiments across three public WiFi datasets reveal that WECAR not only outperforms several state-of-the-art methods in performance and parameter efficiency, but also achieves a substantial reduction in the model's parameter count post-optimization without sacrificing accuracy. This validates its practicality for resource-constrained environments.

cs.LG↗

arXiv2025

Mobility-Aware Decentralized Federated Learning with Joint Optimization of Local Iteration and Leader Selection for Vehicular Networks

Federated learning (FL) emerges as a promising approach to empower vehicular networks, composed by intelligent connected vehicles equipped with advanced sensing, computing, and communication capabilities. While previous studies have explored the application of FL in vehicular networks, they have largely overlooked the intricate challenges arising from the mobility of vehicles and resource constraints. In this paper, we propose a framework of mobility-aware decentralized federated learning (MDFL) for vehicular networks. In this framework, nearby vehicles train an FL model collaboratively, yet in a decentralized manner. We formulate a local iteration and leader selection joint optimization problem (LSOP) to improve the training efficiency of MDFL. For problem solving, we first reformulate LSOP as a decentralized partially observable Markov decision process (Dec-POMDP), and then develop an effective optimization algorithm based on multi-agent proximal policy optimization (MAPPO) to solve Dec-POMDP. Finally, we verify the performance of the proposed algorithm by comparing it with other algorithms.

cs.NI↗

arXiv2024

Affinity-Graph-Guided Contractive Learning for Pretext-Free Medical Image Segmentation with Minimal Annotation

The combination of semi-supervised learning (SemiSL) and contrastive learning (CL) has been successful in medical image segmentation with limited annotations. However, these works often rely on pretext tasks that lack the specificity required for pixel-level segmentation, and still face overfitting issues due to insufficient supervision signals resulting from too few annotations. Therefore, this paper proposes an affinity-graph-guided semi-supervised contrastive learning framework (Semi-AGCL) by establishing additional affinity-graph-based supervision signals between the student and teacher network, to achieve medical image segmentation with minimal annotations without pretext. The framework first designs an average-patch-entropy-driven inter-patch sampling method, which can provide a robust initial feature space without relying on pretext tasks. Furthermore, the framework designs an affinity-graph-guided loss function, which can improve the quality of the learned representation and the model generalization ability by exploiting the inherent structure of the data, thus mitigating overfitting. Our experiments indicate that with merely 10% of the complete annotation set, our model approaches the accuracy of the fully annotated baseline, manifesting a marginal deviation of only 2.52%. Under the stringent conditions where only 5% of the annotations are employed, our model exhibits a significant enhancement in performance surpassing the second best baseline by 23.09% on the dice metric and achieving an improvement of 26.57% on the notably arduous CRAG and ACDC datasets.

cs.CV↗

arXiv2024

Online Learning for Intelligent Thermal Management of Interference-coupled and Passively Cooled Base Stations

Passively cooled base stations (PCBSs) have emerged to deliver better cost and energy efficiency. However, passive cooling necessitates intelligent thermal control via traffic management, i.e., the instantaneous data traffic or throughput of a PCBS directly impacts its thermal performance. This is particularly challenging for outdoor deployment of PCBSs because the heat dissipation efficiency is uncertain and fluctuates over time. What is more, the PCBSs are interference-coupled in multi-cell scenarios. Thus, a higher-throughput PCBS leads to higher interference to the other PCBSs, which, in turn, would require more resource consumption to meet their respective throughput targets. In this paper, we address online decision-making for maximizing the total downlink throughput for a multi-PCBS system subject to constraints related on operating temperature. We demonstrate that a reinforcement learning (RL) approach, specifically soft actor-critic (SAC), can successfully perform throughput maximization while keeping the PCBSs cool, by adapting the throughput to time-varying heat dissipation conditions. Furthermore, we design a denial and reward mechanism that effectively mitigates the risk of overheating during the exploration phase of RL. Simulation results show that our approach achieves up to 88.6% of the global optimum. This is very promising, as our approach operates without prior knowledge of future heat dissipation efficiency, which is required by the global optimum.

cs.NI↗

arXiv2024

Progressive Domain Adaptation for Thermal Infrared Object Tracking

Due to the lack of large-scale labeled Thermal InfraRed (TIR) training datasets, most existing TIR trackers are trained directly on RGB datasets. However, tracking methods trained on RGB datasets suffer a significant drop-off in TIR data due to the domain shift issue. To this end, in this work, we propose a Progressive Domain Adaptation framework for TIR Tracking (PDAT), which transfers useful knowledge learned from RGB tracking to TIR tracking. The framework makes full use of large-scale labeled RGB datasets without requiring time-consuming and labor-intensive labeling of large-scale TIR data. Specifically, we first propose an adversarial-based global domain adaptation module to reduce domain gap on the feature level coarsely. Second, we design a clustering-based subdomain adaptation method to further align the feature distributions of the RGB and TIR datasets finely. These two domain adaptation modules gradually eliminate the discrepancy between the two domains, and thus learn domain-invariant fine-grained features through progressive training. Additionally, we collect a largescale TIR dataset with over 1.48 million unlabeled TIR images for training the proposed domain adaptation framework. Experimental results on five TIR tracking benchmarks show that the proposed method gains a nearly 6% success rate, demonstrating its effectiveness.

cs.CV↗

arXiv2023

Task Offloading Optimization in Mobile Edge Computing under Uncertain Processing Cycles and Intermittent Communications

Mobile edge computing (MEC) has been regarded as a promising approach to deal with explosive computation requirements by enabling cloud computing capabilities at the edge of networks. Existing models of MEC impose some strong assumptions on the known processing cycles and unintermittent communications. However, practical MEC systems are constrained by various uncertainties and intermittent communications, rendering these assumptions impractical. In view of this, we investigate how to schedule task offloading in MEC systems with uncertainties. First, we derive a closed-form expression of the average offloading success probability in a device-to-device (D2D) assisted MEC system with uncertain computation processing cycles and intermittent communications. Then, we formulate a task offloading maximization problem (TOMP), and prove that the problem is NP-hard. For problem solving, if the problem instance exhibits a symmetric structure, we propose a task scheduling algorithm based on dynamic programming (TSDP). By solving this problem instance, we derive a bound to benchmark sub-optimal algorithm. For general scenarios, by reformulating the problem, we propose a repeated matching algorithm (RMA). Finally, in performance evaluations, we validate the accuracy of the closed-form expression of the average offloading success probability by Monte Carlo simulations, as well as the effectiveness of the proposed algorithms.

cs.NI↗

arXiv2023

Robust Divergence Angle for Inter-satellite Laser Communications under Target Deviation Uncertainty

Performance degradation due to target deviation by, for example, drift or jitter, presents a significant issue to inter-satellite laser communications. In particular, with periodic acquisition for positioning the satellite receiver, deviation may arise in the time period between two consecutive acquisition operations. One solution to mitigate the issue is to use a divergence angle at the transmitter being wider than that if the receiver position is perfectly known. However, as how the deviation would vary over time is generally very hard to predict or model, there is no clear clue for setting the divergence angle. We propose a robust optimization approach to the problem, with the advantage that no distribution of the deviation need to be modelled. Instead, a so-called uncertainty set (often defined in form of a convex set such as a polytope) is used, where each element represents a possible scenario, i.e., a sequence of deviation values over time. Robust optimization seeks the solution that maximizes the performance (e.g., sum rate) that can be guaranteed, no matter which scenario in the uncertainty set materializes. To solve the robust optimization problem, we deploy a process of alternately solving a decision maker's problem and an adversarial problem. The former optimizes the divergence angle for a subset of the uncertainty set, whereas the latter is used to explore if the subset needs to be augmented. Simulation results show the approach leads to significantly more robust performance than using the divergence angle as if there is no deviation, or other ad-hoc schemes.

eess.SP↗

arXiv2023

Less Carbon Footprint in Edge Computing by Joint Task Offloading and Energy Sharing

In sprite the state-of-the-art, significantly reducing carbon footprint (CF) in communications systems remains urgent. We address this challenge in the context of edge computing. The carbon intensity of electricity supply largely varies spatially as well as temporally. This, together with energy sharing via a battery management system (BMS), justifies the potential of CF-oriented task offloading, by redistributing the computational tasks in time and space. In this paper, we consider optimal task scheduling and offloading, as well as battery charging to minimize the total CF. We formulate this CF minimization problem as an integer linear programming model. However, we demonstrate that, via a graph-based reformulation, the problem can be cast as a minimum-cost flow problem. This finding reveals that global optimum can be admitted in polynomial time. Numerical results using real-world data show that optimization can reduce up to 83.3% of the total CF.

cs.DC↗

arXiv2022

Multi-cell Content Caching: Optimization for Cost and Information Freshness

In multi-access edge computing (MEC) systems, there are multiple local cache servers caching contents to satisfy the users' requests, instead of letting the users download via the remote cloud server. In this paper, a multi-cell content scheduling problem (MCSP) in MEC systems is considered. Taking into account jointly the freshness of the cached contents and the traffic data costs, we study how to schedule content updates along time in a multi-cell setting. Different from single-cell scenarios, a user may have multiple candidate local cache servers, and thus the caching decisions in all cells must be jointly optimized. We first prove that MCSP is NP-hard, then we formulate MCSP using integer linear programming, by which the optimal scheduling can be obtained for small-scale instances. For problem solving of large scenarios, via a mathematical reformulation, we derive a scalable optimization algorithm based on repeated column generation. Our performance evaluation shows the effectiveness of the proposed algorithm in comparison to an off-the-shelf commercial solver and a popularity-based caching.

cs.IT↗

arXiv2022

Resource Optimization with Interference Coupling in Multi-RIS-assisted Multi-cell Systems

Deploying reconfigurable intelligent surface (RIS) to enhance wireless transmission is a promising approach. In this paper, we investigate large-scale multi-RIS-assisted multi-cell systems, where multiple RISs are deployed in each cell. Different from the full-buffer scenario, the mutual interference in our system is not known a priori, and for this reason we apply the load coupling model to analyze this system. The objective is to minimize the total resource consumption subject to user demand requirement by optimizing the reflection coefficients in the cells. The cells are highly coupled and the overall problem is non-convex. To tackle this, we first investigate the single-cell case with given interference, and propose a low-complexity algorithm based on the Majorization-Minimization method to obtain a locally optimal solution. Then, we embed this algorithm into an algorithmic framework for the overall multi-cell problem, and prove its feasibility and convergence to a solution that is at least locally optimal. Simulation results demonstrate the benefit of RIS in time-frequency resource utilization in the multi-cell system.

cs.IT↗

arXiv2022

QoS Aware Robot Trajectory Optimization with IRS-Assisted Millimeter-Wave Communications

In this paper, we consider the motion energy minimization problem for a robot that uses millimeter-wave (mm-wave) communications assisted by an intelligent reflective surface (IRS). The robot must perform tasks within given deadlines and it is subject to uplink quality of service (QoS) constraints. This problem is crucial for fully automated factories that are governed by the binomial of autonomous robots and new generations of mobile communications, i.e., 5G and 6G. In this new context, robot energy efficiency and communication reliability remain fundamental problems that couple in optimizing robot trajectory and communication QoS. More precisely, to account for the mutual dependency between robot position and communication QoS, robot trajectory and beamforming at the IRS and access point all need to be optimized. We present a solution that can decouple the two problems by exploiting mm-wave channel characteristics. Then, a closed-form solution is obtained for the beamforming optimization problem, whereas the trajectory is optimized by a novel successive-convex optimization-based algorithm that can deal with abrupt line-of-sight (LOS) to non-line-of-sight (NLOS) transitions. Specifically, the algorithm uses a radio map to avoid collisions with obstacles and poorly covered areas. We prove that the algorithm can converge to a solution satisfying the Karush-Kuhn-Tucker conditions. The simulation results show a fast convergence rate of the algorithm and a dramatic reduction of the motion energy consumption with respect to methods that aim to find maximum-rate trajectories. Moreover, we show that the use of passive IRSs represents a powerful solution to improve the radio coverage and motion energy efficiency of robots.

cs.NI↗

arXiv2022

Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking

Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a maximum overlap method based on an intersection-over-union (IoU) loss to mitigate this problem, there are defects in the IoU loss itself, that make it impossible to continue to optimize the objective function when a given bounding box is completely contained within/without another bounding box; this makes it very challenging to accurately estimate the target state. Accordingly, in this paper, we address the above-mentioned problem by proposing a novel tracking method based on a distance-IoU (DIoU) loss, such that the proposed tracker consists of target estimation and target classification. The target estimation part is trained to predict the DIoU score between the target ground-truth bounding-box and the estimated bounding-box. The DIoU loss can maintain the advantage provided by the IoU loss while minimizing the distance between the center points of two bounding boxes, thereby making the target estimation more accurate. Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed. Comprehensive experimental results demonstrate that the proposed method achieves competitive tracking accuracy when compared to state-of-the-art trackers while with a real-time tracking speed.

cs.CV↗

arXiv2022

Active Learning for Deep Visual Tracking

Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly affect the representational capability of the trained model. However, this approach is restrictive in practice, because manually labeling such a large number of training samples is time-consuming and prohibitively expensive. In this paper, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNNs model. Under the guidance of active learning, the tracker based on the trained deep CNNs model can achieve competitive tracking performance while reducing the labeling cost. More specifically, to ensure the diversity of selected samples, we propose an active learning method based on multi-frame collaboration to select those training samples that should be and need to be annotated. Meanwhile, considering the representativeness of these selected samples, we adopt a nearest neighbor discrimination method based on the average nearest neighbor distance to screen isolated samples and low-quality samples. Therefore, the training samples subset selected based on our method requires only a given budget to maintain the diversity and representativeness of the entire sample set. Furthermore, we adopt a Tversky loss to improve the bounding box estimation of our tracker, which can ensure that the tracker achieves more accurate target states. Extensive experimental results confirm that our active learning-based tracker (ALT) achieves competitive tracking accuracy and speed compared with state-of-the-art trackers on the seven most challenging evaluation benchmarks.

cs.CV↗

arXiv2021

Optimal Content Caching and Recommendation with Age of Information

Content caching at the network edge has been considered an effective way of mitigating backhaul load and improving user experience. Caching efficiency can be enhanced by content recommendation and by keeping the information fresh. To the best of our knowledge, there is no work that jointly takes into account these aspects. By content recommendation, a requested content that is not in the cache can be alternatively satisfied by a related cached content recommended by the system. Information freshness can be quantified by age of information (AoI). We address, optimal scheduling of cache updates for a time-slotted system accounting for content recommendation and AoI. For each content, there are requests that need to be satisfied, and there is a cost function capturing the freshness of information. We present the following contributions. First, we prove that the problem is NP-hard. Second, we derive an integer linear formulation, by which the optimal solution can be obtained for small-scale scenarios. Third, we develop an algorithm based on Lagrangian decomposition. Fourth, we develop efficient algorithms for solving the resulting subproblems. Our algorithm computes a bound that can be used to evaluate the performance of any suboptimal solution. Finally, we conduct simulations to show the effectiveness of our algorithm in comparison to a greedy schedule.

cs.NI↗