arXiv subjects

Ming Zhao

Publications and source records attributed to Ming Zhao.

At least 55 records · Page 3Linked to original sources

arXiv2025

InSlicing: Interpretable Learning-Assisted Network Slice Configuration in Open Radio Access Networks

Network slicing is a key technology enabling the flexibility and efficiency of 5G networks, offering customized services for diverse applications. However, existing methods face challenges in adapting to dynamic network environments and lack interpretability in performance models. In this paper, we propose a novel interpretable network slice configuration algorithm (\emph{InSlicing}) in open radio access networks, by integrating Kolmogorov-Arnold Networks (KANs) and hybrid optimization process. On the one hand, we use KANs to approximate and learn the unknown performance function of individual slices, which converts the blackbox optimization problem. On the other hand, we solve the converted problem with a genetic method for global search and incorporate a trust region for gradient-based local refinement. With the extensive evaluation, we show that our proposed algorithm achieves high interpretability while reducing 25+\% operation cost than existing solutions.

cs.NI↗

arXiv2025

6G comprehensive intelligence: network operations and optimization based on Large Language Models

The sixth generation mobile communication standard (6G) can promote the development of Industrial Internet and Internet of Things (IoT). To achieve comprehensive intelligent development of the network and provide customers with higher quality personalized services. This paper proposes a network performance optimization and intelligent operation network architecture based on Large Language Model (LLM), aiming to build a comprehensive intelligent 6G network system. The Large Language Model, with more parameters and stronger learning ability, can more accurately capture patterns and features in data, which can achieve more accurate content output and high intelligence and provide strong support for related research such as network data security, privacy protection, and health assessment. This paper also presents the design framework of a network health assessment system based on LLM and focuses on its potential application value, through the case of network health management system, it is fully demonstrated that the 6G intelligent network system based on LLM has important practical significance for the comprehensive realization of intelligence.

cs.NI↗

arXiv2025

Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documents

The 3rd Generation Partnership Project (3GPP) documents is key standards in global telecommunications, while posing significant challenges for engineers and researchers in the telecommunications field due to the large volume and complexity of their contents as well as the frequent updates. Large language models (LLMs) have shown promise in natural language processing tasks, but their general-purpose nature limits their effectiveness in specific domains like telecommunications. To address this, we propose Chat3GPP, an open-source retrieval-augmented generation (RAG) framework tailored for 3GPP specifications. By combining chunking strategies, hybrid retrieval and efficient indexing methods, Chat3GPP can efficiently retrieve relevant information and generate accurate responses to user queries without requiring domain-specific fine-tuning, which is both flexible and scalable, offering significant potential for adapting to other technical standards beyond 3GPP. We evaluate Chat3GPP on two telecom-specific datasets and demonstrate its superior performance compared to existing methods, showcasing its potential for downstream tasks like protocol generation and code automation.

cs.CL↗

arXiv2025

AdaSlicing: Adaptive Online Network Slicing under Continual Network Dynamics in Open Radio Access Networks

Open radio access networks (e.g., O-RAN) facilitate fine-grained control (e.g., near-RT RIC) in next-generation networks, necessitating advanced AI/ML techniques in handling online resource orchestration in real-time. However, existing approaches can hardly adapt to time-evolving network dynamics in network slicing, leading to significant online performance degradation. In this paper, we propose AdaSlicing, a new adaptive network slicing system, to online learn to orchestrate virtual resources while efficiently adapting to continual network dynamics. The AdaSlicing system includes a new soft-isolated RAN virtualization framework and a novel AdaOrch algorithm. We design the AdaOrch algorithm by integrating AI/ML techniques (i.e., Bayesian learning agents) and optimization methods (i.e., the ADMM coordinator). We design the soft-isolated RAN virtualization to improve the virtual resource utilization of slices while assuring the isolation among virtual resources at runtime. We implement AdaSlicing on an O-RAN compliant network testbed by using OpenAirInterface RAN, Open5GS Core, and FlexRIC near-RT RIC, with Ettus USRP B210 SDR. With extensive network experiments, we demonstrate that AdaSlicing substantially outperforms state-of-the-art works with 64.2% cost reduction and 45.5% normalized performance improvement, which verifies its high adaptability, scalability, and assurance.

cs.NI↗

arXiv2024

DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement

In the Fourier frequency domain, luminance information is primarily encoded in the amplitude component, while spatial structure information is significantly contained within the phase component. Existing low-light image enhancement techniques using Fourier transform have mainly focused on amplifying the amplitude component and simply replicating the phase component, an approach that often leads to color distortions and noise issues. In this paper, we propose a Dual-Stage Multi-Branch Fourier Low-Light Image Enhancement (DMFourLLIE) framework to address these limitations by emphasizing the phase component's role in preserving image structure and detail. The first stage integrates structural information from infrared images to enhance the phase component and employs a luminance-attention mechanism in the luminance-chrominance color space to precisely control amplitude enhancement. The second stage combines multi-scale and Fourier convolutional branches for robust image reconstruction, effectively recovering spatial structures and textures. This dual-branch joint optimization process ensures that complex image information is retained, overcoming the limitations of previous methods that neglected the interplay between amplitude and phase. Extensive experiments across multiple datasets demonstrate that DMFourLLIE outperforms current state-of-the-art methods in low-light image enhancement. Our code is available at https://github.com/bywlzts/DMFourLLIE.

cs.CV↗

arXiv2024

Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval

Remote sensing cross-modal text-image retrieval (RSCTIR) has gained attention for its utility in information mining. However, challenges remain in effectively integrating global and local information due to variations in remote sensing imagery and ensuring proper feature pre-alignment before modal fusion, which affects retrieval accuracy and efficiency. To address these issues, we propose CMPAGL, a cross-modal pre-aligned method leveraging global and local information. Our Gswin transformer block combines local window self-attention and global-local window cross-attention to capture multi-scale features. A pre-alignment mechanism simplifies modal fusion training, improving retrieval performance. Additionally, we introduce a similarity matrix reweighting (SMR) algorithm for reranking, and enhance the triplet loss function with an intra-class distance term to optimize feature learning. Experiments on four datasets, including RSICD and RSITMD, validate CMPAGL's effectiveness, achieving up to 4.65% improvement in R@1 and 2.28% in mean Recall (mR) over state-of-the-art methods.

cs.CV↗

arXiv2024

Multitask Learning for SAR Ship Detection with Gaussian-Mask Joint Segmentation

Detecting ships in synthetic aperture radar (SAR) images is challenging due to strong speckle noise, complex surroundings, and varying scales. This paper proposes MLDet, a multitask learning framework for SAR ship detection, consisting of object detection, speckle suppression, and target segmentation tasks. An angle classification loss with aspect ratio weighting is introduced to improve detection accuracy by addressing angular periodicity and object proportions. The speckle suppression task uses a dual-feature fusion attention mechanism to reduce noise and fuse shallow and denoising features, enhancing robustness. The target segmentation task, leveraging a rotated Gaussian-mask, aids the network in extracting target regions from cluttered backgrounds and improves detection efficiency with pixel-level predictions. The Gaussian-mask ensures ship centers have the highest probabilities, gradually decreasing outward under a Gaussian distribution. Additionally, a weighted rotated boxes fusion (WRBF) strategy combines multi-direction anchor predictions, filtering anchors beyond boundaries or with high overlap but low confidence. Extensive experiments on SSDD+ and HRSID datasets demonstrate the effectiveness and superiority of MLDet.

cs.CV↗

arXiv2024

A Zoned Storage Optimized Flash Cache on ZNS SSDs

Zoned Namespace SSDs (ZNS) are introduced recently to mitigate the block interface penalties of flash-based SSDs. It is a good opportunity for flash cache to address cache throughput and write amplification (WA) issues by fully controlling data allocation and garbage collection via zone-based interfaces. However, there are several critical challenges that need to be addressed including zone-interface compatibility, data management of large zone size, and a better tradeoff between throughput, cache hit ratio, and WA. In this paper, we present Z-CacheLib, a zoned storage optimized flash cache on ZNS SSDs. In Z-CacheLib, we propose: 1) a new zStorage Engine for ZNS SSDs with low mapping and operational overhead, and 2) a novel zCache Engine with cross-layer optimizations to resolve the throughput regression and WA issues of garbage collection, which consists of delayed data eviction with virtual over-provisioning (vOP), a top-down eviction policy (zLRU) optimized from LRU, and a bottom-up drop mechanism (zDrop) for low WA. Our evaluation shows that Z-CacheLib can achieve up to 2X throughput, 5% improvement hit ratio, and almost no WA compared to CacheLib with compatible regular SSDs, demonstrating benefits of using ZNS SSDs for cache. Moreover, Z-CacheLib can achieve up to 6X throughput and 92% WA reduction compared with F2FS-based scheme.

cs.PF↗

arXiv2024

AlN/Si interface engineering to mitigate RF losses in MOCVD grown GaN-on-Si substrates

Fabrication of low-RF loss GaN-on-Si HEMT stacks is critical to enable competitive front-end-modules for 5G and 6G applications. The main contribution to RF losses is the interface between the III-N layer and the HR Si wafer, more specifically the AlN/Si interface. At this interface, a parasitic surface conduction layer exists in Si, which decreases the substrate effective resistivity sensed by overlying circuitry below the nominal Si resistivity. However, a clear understanding of this interface with control of the parasitic channel is lacking. In this letter, a detailed physical and electrical description of MOCVD-grown AlN/Si structures is presented. The presence of a $\text{SiC}_\text{x}\text{N}_\text{y}$ interfacial layer is revealed and its importance for RF losses is shown. Through C-V and I-V characterisation, an increase in the C concentration of this interfacial layer is linked to the formation of negative charge at the AlN/Si interface, which counteracts the positive charge present in the 0-predose limit. The variation of TMAl predose is shown to allow precise tuning of the C composition and, consequently, the resulting interface charge. Notably, a linear relationship between predose and net interface charge is observed and confirmed by the fabrication of an AlN/Si sample with close to zero net charge. In addition, a higher $D_{it}$ ($\sim 2\times 10^{12}$ cm$^\text{-2}$) for such compensated samples is observed and can contribute to low RF loss. An exceptionally high effective resistivity of above 8 k$Ω\cdot$cm is achieved, corresponding to an RF loss below 0.3 dB/mm at 10 GHz.

physics.app-ph↗

arXiv2024

LeFi: Learn to Incentivize Federated Learning in Automotive Edge Computing

Federated learning (FL) is the promising privacy-preserve approach to continually update the central machine learning (ML) model (e.g., object detectors in edge servers) by aggregating the gradients obtained from local observation data in distributed connected and automated vehicles (CAVs). The incentive mechanism is to incentivize individual selfish CAVs to participate in FL towards the improvement of overall model accuracy. It is, however, challenging to design the incentive mechanism, due to the complex correlation between the overall model accuracy and unknown incentive sensitivity of CAVs, especially under the non-independent and identically distributed (Non-IID) data of individual CAVs. In this paper, we propose a new learn-to-incentivize algorithm to adaptively allocate rewards to individual CAVs under unknown sensitivity functions. First, we gradually learn the unknown sensitivity function of individual CAVs with accumulative observations, by using compute-efficient Gaussian process regression (GPR). Second, we iteratively update the reward allocation to individual CAVs with new sampled gradients, derived from GPR. Third, we project the updated reward allocations to comply with the total budget. We evaluate the performance of extensive simulations, where the simulation parameters are obtained from realistic profiling of the CIFAR-10 dataset and NVIDIA RTX 3080 GPU. The results show that our proposed algorithm substantially outperforms existing solutions, in terms of accuracy, scalability, and adaptability.

cs.NI↗

arXiv2024

Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks

The Space-Air-Ground Integrated Network (SAGIN) plays a pivotal role as a comprehensive foundational network communication infrastructure, presenting opportunities for highly efficient global data transmission. Nonetheless, given SAGIN's unique characteristics as a dynamically heterogeneous network, conventional network optimization methodologies encounter challenges in satisfying the stringent requirements for network latency and stability inherent to data transmission within this network environment. Therefore, this paper proposes the use of differentiated federated reinforcement learning (DFRL) to solve the traffic offloading problem in SAGIN, i.e., using multiple agents to generate differentiated traffic offloading policies. Considering the differentiated characteristics of each region of SAGIN, DFRL models the traffic offloading policy optimization process as the process of solving the Decentralized Partially Observable Markov Decision Process (DEC-POMDP) problem. The paper proposes a novel Differentiated Federated Soft Actor-Critic (DFSAC) algorithm to solve the problem. The DFSAC algorithm takes the network packet delay as the joint reward value and introduces the global trend model as the joint target action-value function of each agent to guide the update of each agent's policy. The simulation results demonstrate that the traffic offloading policy based on the DFSAC algorithm achieves better performance in terms of network throughput, packet loss rate, and packet delay compared to the traditional federated reinforcement learning approach and other baseline approaches.

cs.NI↗

arXiv2024

Bias of AI-Generated Content: An Examination of News Produced by Large Language Models

Large language models (LLMs) have the potential to transform our lives and work through the content they generate, known as AI-Generated Content (AIGC). To harness this transformation, we need to understand the limitations of LLMs. Here, we investigate the bias of AIGC produced by seven representative LLMs, including ChatGPT and LLaMA. We collect news articles from The New York Times and Reuters, both known for their dedication to provide unbiased news. We then apply each examined LLM to generate news content with headlines of these news articles as prompts, and evaluate the gender and racial biases of the AIGC produced by the LLM by comparing the AIGC and the original news articles. We further analyze the gender bias of each LLM under biased prompts by adding gender-biased messages to prompts constructed from these news headlines. Our study reveals that the AIGC produced by each examined LLM demonstrates substantial gender and racial biases. Moreover, the AIGC generated by each LLM exhibits notable discrimination against females and individuals of the Black race. Among the LLMs, the AIGC generated by ChatGPT demonstrates the lowest level of bias, and ChatGPT is the sole model capable of declining content generation when provided with biased prompts.

cs.AI↗

arXiv2024

Towards Practical Requirement Analysis and Verification: A Case Study on Software IP Components in Aerospace Embedded Systems

IP-based software design is a crucial research field that aims to improve efficiency and reliability by reusing complex software components known as intellectual property (IP) components. To ensure the reusability of these components, particularly in security-sensitive software systems, it is necessary to analyze the requirements and perform formal verification for each IP component. However, converting the requirements of IP components from natural language descriptions to temporal logic and subsequently conducting formal verification demands domain expertise and non-trivial manpower. This paper presents a case study on software IP components derived from aerospace embedded systems, with the objective of automating the requirement analysis and verification process. The study begins by employing Large Language Models to convert unstructured natural language into formal specifications. Subsequently, three distinct verification techniques are employed to ascertain whether the source code meets the extracted temporal logic properties. By doing so, five real-world IP components from the China Academy of Space Technology (CAST) have been successfully verified.

cs.SE↗

arXiv2024

Self-Supervised Quantization-Aware Knowledge Distillation

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper-parameter tuning to balance the weights of different loss terms, assume the availability of labeled training data, and require complex, computationally intensive training procedures for good performance. To address these limitations, this paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation (SQAKD) framework. SQAKD first unifies the forward and backward dynamics of various quantization functions, making it flexible for incorporating various QAT works. Then it formulates QAT as a co-optimization problem that simultaneously minimizes the KL-Loss between the full-precision and low-bit models for KD and the discretization error for quantization, without supervision from labels. A comprehensive evaluation shows that SQAKD substantially outperforms the state-of-the-art QAT and KD works for a variety of model architectures. Our code is at: https://github.com/kaiqi123/SQAKD.git.

cs.LG↗

arXiv2023

LiDAR-based Outdoor Crowd Management for Smart Campus on the Edge

Crowd management is crucial for a smart campus. Popular methods are camera-based. However, conventional camera-based approaches may leak users' personally identifiable features, jeopardizing user's privacy, which limits its application. In this work, we investigate using affordable light detection and ranging (LiDAR) technology to perform outdoor crowd management leveraging edge computing. Specifically, we aim to count the number of people on a walkway of a university campus. Besides privacy protection, LiDAR sensors are superior to cameras since their performance will not be compromised when the campus is not well-illuminated. We deploy LiDAR sensors on light poles to collect data from the crowd on the campus and leverage edge accelerators to process data locally. We proposed two different methodologies in this work: 1) a non-convolutional neural network (CNN)-based approach, using clustering and autoencoder, and 2) a CNN-based approach that first projects point clouds to 2D planes and then processes the projection with conventional CNNs. Our first approach relies on careful feature engineering, whereas our second approach does not require such effort. However, the CNN-based approach requires more computational power than our non-CNN-based approach. We evaluate both approaches comprehensively with our hand-labeled real-life data collected from campus. Our evaluation results show that the first method achieves an accuracy of 85.4%, whereas the second method achieves 95.8%. Our CNN-based method outperforms existing solutions significantly. We also deploy our two models on an edge accelerator, TPU, to measure the speedup, leveraging this specialized accelerator.

cs.CV↗

arXiv2023

Learn to Augment Network Simulators Towards Digital Network Twins

Digital network twin (DNT) is a promising paradigm to replicate real-world cellular networks toward continual assessment, proactive management, and what-if analysis. Existing discussions have been focusing on using only deep learning techniques to build DNTs, which raises widespread concerns regarding their generalization, explainability, and transparency. In this paper, we explore an alternative approach to augment network simulators with context-aware neural agents. The main challenge lies in the non-trivial simulation-to-reality (sim-to-real) discrepancy between offline simulators and real-world networks. To solve the challenge, we propose a new learn-to-bridge algorithm to cost-efficiently bridge the sim-to-real discrepancy in two alternative stages. In the first stage, we select states to query performances in real-world networks by using newly-designed cost-aware Bayesian optimization. In the second stage, we train the neural agent to learn the state context and bridge the probabilistic discrepancy based on Bayesian neural networks (BNN). In addition, we build a small-scale end-to-end network testbed based on OpenAirInterface RAN and Core with USRP B210 and a smartphone, and replicate the network in NS-3. The evaluation results show that, our proposed solution substantially outperforms existing methods, with more than 92\% reduction in the sim-to-real discrepancy.

cs.NI↗

arXiv2023

Poster: Self-Supervised Quantization-Aware Knowledge Distillation

Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining. However, existing QAT works require supervision from the labels and they suffer from accuracy loss due to reduced precision. To address these limitations, this paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation framework (SQAKD). SQAKD first unifies the forward and backward dynamics of various quantization functions and then reframes QAT as a co-optimization problem that simultaneously minimizes the KL-Loss and the discretization error, in a self-supervised manner. The evaluation shows that SQAKD significantly improves the performance of various state-of-the-art QAT works. SQAKD establishes stronger baselines and does not require extensive labeled training data, potentially making state-of-the-art QAT research more accessible.

cs.CV↗

arXiv2023

UniSA: Unified Generative Framework for Sentiment Analysis

Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information. It consists of several subtasks, such as emotion recognition in conversation (ERC), aspect-based sentiment analysis (ABSA), and multimodal sentiment analysis (MSA). However, unifying all subtasks in sentiment analysis presents numerous challenges, including modality alignment, unified input/output forms, and dataset bias. To address these challenges, we propose a Task-Specific Prompt method to jointly model subtasks and introduce a multimodal generative framework called UniSA. Additionally, we organize the benchmark datasets of main subtasks into a new Sentiment Analysis Evaluation benchmark, SAEval. We design novel pre-training tasks and training methods to enable the model to learn generic sentiment knowledge among subtasks to improve the model's multimodal sentiment perception ability. Our experimental results show that UniSA performs comparably to the state-of-the-art on all subtasks and generalizes well to various subtasks in sentiment analysis.

cs.CL↗