arXiv subjects

Lian Zhao

Publications and source records attributed to Lian Zhao.

At least 19 recordsLinked to original sources

arXiv2026

ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality

We present ResLearn-XR, a residual learning framework for predicting eXtended Reality (XR) network traffic and estimating Quality-of-Experience (QoE) risk. ResLearn-XR adopts a two-stage temporal learning structure comprising a base sequence prediction model augmented with task-specific residual learning components to improve adaptability to bursty, non-stationary XR traffic dynamics. The residual learning stages operate in the value space for continuous XR traffic forecasting and in the logit space for probabilistic QoE risk estimation. \rev{For the QoE-risk branch, we introduce a Data Descriptor Algorithm (DDA), a causal feature-construction module that converts packet-level application-layer observables into frame-timing-aware descriptors suitable for encrypted traffic analysis. We also construct an XR Traffic-QoE dataset that pairs continuous XR traffic traces with session-level user-reported QoE labels. ResLearn-XR reduces SMAPE by up to 17.84% across frame-count, frame-size, and inter-arrival-time prediction, while reducing QoE-risk estimation SMAPE by up to 87.8% over single-stage baselines.

cs.AI↗

arXiv2025

HQ-MPSD: A Multilingual Artifact-Controlled Benchmark for Partial Deepfake Speech Detection

Detecting partial deepfake speech is challenging because manipulations occur only in short regions while the surrounding audio remains authentic. However, existing detection methods are fundamentally limited by the quality of available datasets, many of which rely on outdated synthesis systems and generation procedures that introduce dataset-specific artifacts rather than realistic manipulation cues. To address this gap, we introduce HQ-MPSD, a high-quality multilingual partial deepfake speech dataset. HQ-MPSD is constructed using linguistically coherent splice points derived from fine-grained forced alignment, preserving prosodic and semantic continuity and minimizing audible and visual boundary artifacts. The dataset contains 350.8 hours of speech across eight languages and 550 speakers, with background effects added to better reflect real-world acoustic conditions. MOS evaluations and spectrogram analysis confirm the high perceptual naturalness of the samples. We benchmark state-of-the-art detection models through cross-language and cross-dataset evaluations, and all models experience performance drops exceeding 80% on HQ-MPSD. These results demonstrate that HQ-MPSD exposes significant generalization challenges once low-level artifacts are removed and multilingual and acoustic diversity are introduced, providing a more realistic and demanding benchmark for partial deepfake detection. The dataset can be found at: https://zenodo.org/records/17929533.

cs.SD↗

arXiv2025

QLook:Quantum-Driven Viewport Prediction for Virtual Reality

We propose QLook, a quantum-driven predictive framework to improve viewport prediction accuracy in immersive virtual reality (VR) environments. The framework utilizes quantum neural networks (QNNs) to model the user movement data, which has multiple interdependent dimensions and is collected in six-degree-of-freedom (6DoF) VR settings. QNN leverages superposition and entanglement to encode and process complex correlations among high-dimensional user positional data. The proposed solution features a cascaded hybrid architecture that integrates classical neural networks with variational quantum circuits (VQCs)-enhanced quantum long short-term memory (QLSTM) networks. We utilize identity block initialization to mitigate training challenges commonly associated with VQCs, particularly those encountered as barren plateaus. Empirical evaluation of QLook demonstrates a 37.4% reduction in mean squared error (MSE) compared to state-of-the-art (SoTA), showcasing superior viewport prediction.

quant-ph↗

arXiv2025

Frame-level Temporal Difference Learning for Partial Deepfake Speech Detection

Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, limiting real-world scalability. Also, they focus on detecting transition artifacts between bonafide and deepfake segments. As deepfake generation techniques increasingly smooth these transitions, detection has become more challenging. To address this, our work introduces a new perspective by analyzing frame-level temporal differences and reveals that deepfake speech exhibits erratic directional changes and unnatural local transitions compared to bonafide speech. Based on this finding, we propose a Temporal Difference Attention Module (TDAM) that redefines partial deepfake detection as identifying unnatural temporal variations, without relying on explicit boundary annotations. A dual-level hierarchical difference representation captures temporal irregularities at both fine and coarse scales, while adaptive average pooling preserves essential patterns across variable-length inputs to minimize information loss. Our TDAM-AvgPool model achieves state-of-the-art performance, with an EER of 0.59% on the PartialSpoof dataset and 0.03% on the HAD dataset, which significantly outperforms the existing methods without requiring frame-level supervision.

cs.SD↗

arXiv2025

Training Beam Design for Channel Estimation in Hybrid mmWave MIMO Systems

Training beam design for channel estimation with infinite-resolution and low-resolution phase shifters (PSs) in hybrid analog-digital milimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems is considered in this paper. By exploiting the sparsity of mmWave channels, the optimization of the sensing matrices (corresponding to training beams) is formulated according to the compressive sensing (CS) theory. Under the condition of infinite-resolution PSs, we propose relevant algorithms to construct the sensing matrix, where the theory of convex optimization and the gradient descent in Riemannian manifold is used to design the digital and analog part, respectively. Furthermore, a block-wise alternating hybrid analog-digital algorithm is proposed to tackle the design of training beams with low-resolution PSs, where the performance degeneration caused by non-convex constant modulus and discrete phase constraints is effectively compensated to some extent thanks to the iterations among blocks. Finally, the orthogonal matching pursuit (OMP) based estimator is adopted for achieving an effective recovery of the sparse mmWave channel. Simulation results demonstrate the performance advantages of proposed algorithms compared with some existing schemes.

eess.SP↗

arXiv2025

Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classification

In real-world scenarios, multi-view multi-label learning often encounters the challenge of incomplete training data due to limitations in data collection and unreliable annotation processes. The absence of multi-view features impairs the comprehensive understanding of samples, omitting crucial details essential for classification. To address this issue, we present a task-augmented cross-view imputation network (TACVI-Net) for the purpose of handling partial multi-view incomplete multi-label classification. Specifically, we employ a two-stage network to derive highly task-relevant features to recover the missing views. In the first stage, we leverage the information bottleneck theory to obtain a discriminative representation of each view by extracting task-relevant information through a view-specific encoder-classifier architecture. In the second stage, an autoencoder based multi-view reconstruction network is utilized to extract high-level semantic representation of the augmented features and recover the missing data, thereby aiding the final classification task. Extensive experiments on five datasets demonstrate that our TACVI-Net outperforms other state-of-the-art methods.

cs.CV↗

arXiv2025

Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification

Multi-view multi-label classification (MvMLC) has recently garnered significant research attention due to its wide range of real-world applications. However, incompleteness in views and labels is a common challenge, often resulting from data collection oversights and uncertainties in manual annotation. Furthermore, the task of learning robust multi-view representations that are both view-consistent and view-specific from diverse views still a challenge problem in MvMLC. To address these issues, we propose a novel framework for incomplete multi-view multi-label classification (iMvMLC). Our method factorizes multi-view representations into two independent sets of factors: view-consistent and view-specific, and we correspondingly design a graph disentangling loss to fully reduce redundancy between these representations. Additionally, our framework innovatively decomposes consistent representation learning into three key sub-objectives: (i) how to extract view-shared information across different views, (ii) how to eliminate intra-view redundancy in consistent representations, and (iii) how to preserve task-relevant information. To this end, we design a robust task-relevant consistency learning module that collaboratively learns high-quality consistent representations, leveraging a masked cross-view prediction (MCP) strategy and information theory. Notably, all modules in our framework are developed to function effectively under conditions of incomplete views and labels, making our method adaptable to various multi-view and multi-label datasets. Extensive experiments on five datasets demonstrate that our method outperforms other leading approaches.

cs.CV↗

arXiv2024

Discern-XR: An Online Classifier for Metaverse Network Traffic

In this paper, we design an exclusive Metaverse network traffic classifier, named Discern-XR, to help Internet service providers (ISP) and router manufacturers enhance the quality of Metaverse services. Leveraging segmented learning, the Frame Vector Representation (FVR) algorithm and Frame Identification Algorithm (FIA) are proposed to extract critical frame-related statistics from raw network data having only four application-level features. A novel Augmentation, Aggregation, and Retention Online Training (A2R-OT) algorithm is proposed to find an accurate classification model through online training methodology. In addition, we contribute to the real-world Metaverse dataset comprising virtual reality (VR) games, VR video, VR chat, augmented reality (AR), and mixed reality (MR) traffic, providing a comprehensive benchmark. Discern-XR outperforms state-of-the-art classifiers by 7% while improving training efficiency and reducing false-negative rates. Our work advances Metaverse network traffic classification by standing as the state-of-the-art solution.

cs.AI↗

arXiv2024

ResLearn: Transformer-based Residual Learning for Metaverse Network Traffic Prediction

Our work proposes a comprehensive solution for predicting Metaverse network traffic, addressing the growing demand for intelligent resource management in eXtended Reality (XR) services. We first introduce a state-of-the-art testbed capturing a real-world dataset of virtual reality (VR), augmented reality (AR), and mixed reality (MR) traffic, made openly available for further research. To enhance prediction accuracy, we then propose a novel view-frame (VF) algorithm that accurately identifies video frames from traffic while ensuring privacy compliance, and we develop a Transformer-based progressive error-learning algorithm, referred to as ResLearn for Metaverse traffic prediction. ResLearn significantly improves time-series predictions by using fully connected neural networks to reduce errors, particularly during peak traffic, outperforming prior work by 99%. Our contributions offer Internet service providers (ISPs) robust tools for real-time network management to satisfy Quality of Service (QoS) and enhance user experience in the Metaverse.

cs.AI↗

arXiv2024

Time-Distributed Feature Learning for Internet of Things Network Traffic Classification

Deep learning-based network traffic classification (NTC) techniques, including conventional and class-of-service (CoS) classifiers, are a popular tool that aids in the quality of service (QoS) and radio resource management for the Internet of Things (IoT) network. Holistic temporal features consist of inter-, intra-, and pseudo-temporal features within packets, between packets, and among flows, providing the maximum information on network services without depending on defined classes in a problem. Conventional spatio-temporal features in the current solutions extract only space and time information between packets and flows, ignoring the information within packets and flow for IoT traffic. Therefore, we propose a new, efficient, holistic feature extraction method for deep-learning-based NTC using time-distributed feature learning to maximize the accuracy of the NTC. We apply a time-distributed wrapper on deep-learning layers to help extract pseudo-temporal features and spatio-temporal features. Pseudo-temporal features are mathematically complex to explain since, in deep learning, a black box extracts them. However, the features are temporal because of the time-distributed wrapper; therefore, we call them pseudo-temporal features. Since our method is efficient in learning holistic-temporal features, we can extend our method to both conventional and CoS NTC. Our solution proves that pseudo-temporal and spatial-temporal features can significantly improve the robustness and performance of any NTC. We analyze the solution theoretically and experimentally on different real-world datasets. The experimental results show that the holistic-temporal time-distributed feature learning method, on average, is 13.5% more accurate than the state-of-the-art conventional and CoS classifiers.

eess.SP↗

arXiv2024

Unveiling and Controlling Anomalous Attention Distribution in Transformers

With the advent of large models based on the Transformer architecture, researchers have observed an anomalous phenomenon in the Attention mechanism--there is a very high attention on the first element, which is prevalent across Transformer-based models. It is crucial to understand it for the development of techniques focusing on attention distribution, such as Key-Value (KV) Cache compression and infinite extrapolation; however, the latent cause leaves to be unknown. In this paper, we analyze such a phenomenon from the perspective of waiver phenomenon, which involves reducing the internal values of certain elements in the sequence, allowing them to absorb excess attention without affecting their contribution to information. In specific models, due to differences in positional encoding and attention patterns, we have found that the selection of waiver elements by the model can be categorized into two methods: positional-encoding-based and feature-distribution-within-elements-based.

cs.LG↗

arXiv2023

A Unified Joint Optimization of Training Sequences and Transceivers Based on Matrix-Monotonic Optimization

Channel estimation and data transmission constitute the most fundamental functional modules of multiple-input multiple-output (MIMO) communication systems. The underlying key tasks corresponding to these modules are training sequence optimization and transceiver optimization. Hence, we jointly optimize the linear transmit precoder and the training sequence of MIMO systems using the metrics of their effective mutual information (MI), effective mean squared error (MSE), effective weighted MI, effective weighted MSE, as well as their effective generic Schur-convex and Schur-concave functions. Both statistical channel state information (CSI) and estimated CSI are considered at the transmitter in the joint optimization. A unified framework termed as joint matrix-monotonic optimization is proposed. Based on this, the optimal precoder matrix and training matrix structures can be derived for both CSI scenarios. Then, based on the optimal matrix structures, our linear transceivers and their training sequences can be jointly optimized. Compared to state-of-the-art benchmark algorithms, the proposed algorithms visualize the bold explicit relationships between the attainable system performance of our linear transceivers conceived and their training sequences, leading to implementation ready recipes. Finally, several numerical results are provided, which corroborate our theoretical results and demonstrate the compelling benefits of our proposed pilot-aided MIMO solutions.

cs.IT↗

arXiv2022

Random Access with Massive MIMO-OTFS in LEO Satellite Communications

This paper considers the joint channel estimation and device activity detection in the grant-free random access systems, where a large number of Internet-of-Things devices intend to communicate with a low-earth orbit satellite in a sporadic way. In addition, the massive multiple-input multiple-output (MIMO) with orthogonal time-frequency space (OTFS) modulation is adopted to combat the dynamics of the terrestrial-satellite link. We first analyze the input-output relationship of the single-input single-output OTFS when the large delay and Doppler shift both exist, and then extend it to the grant-free random access with massive MIMO-OTFS. Next, by exploring the sparsity of channel in the delay-Doppler-angle domain, a two-dimensional pattern coupled hierarchical prior with the sparse Bayesian learning and covariance-free method (TDSBL-CF) is developed for the channel estimation. Then, the active devices are detected by computing the energy of the estimated channel. Finally, the generalized approximate message passing algorithm combined with the sparse Bayesian learning and two-dimensional convolution (ConvSBL-GAMP) is proposed to decrease the computations of the TDSBL-CF algorithm. Simulation results demonstrate that the proposed algorithms outperform conventional methods.

eess.SP↗

arXiv2021

Collaborative Multi-Resource Allocation in Terrestrial-Satellite Network Towards 6G

Terrestrial-satellite networks are envisioned to play a significant role in the sixth-generation (6G) wireless networks. In such networks, hot air balloons are useful as they can relay the signals between satellites and ground stations. Most existing works assume that the hot air balloons are deployed at the same height with the same minimum elevation angle to the satellites, which may not be practical due to possible route conflict with airplanes and other flight equipment. In this paper, we consider a TSN containing hot air balloons at different heights and with different minimum elevation angles, which creates the challenge of non-uniform available serving time for the communication between the hot air balloons and the satellites. Jointly considering the caching, computing, and communication (3C) resource management for both the ground-balloon-satellite links and inter-satellite laser links, our objective is to maximize the network energy efficiency. Firstly, by proposing a tapped water-filling algorithm, we schedule the traffic to relay among satellites according to the available serving time of satellites. Then, we generate a series of configuration matrices, based on which we formulate the relationship of relay time and the power consumption involved in the relay among satellites. Finally, the integrated system model of TSN is built and solved by geometric programming with Taylor series approximation. Simulation results demonstrate the effectiveness of our proposed scheme.

cs.IT↗

arXiv2020

Deep Reinforcement Learning for Collaborative Edge Computing in Vehicular Networks

Mobile edge computing (MEC) is a promising technology to support mission-critical vehicular applications, such as intelligent path planning and safety applications. In this paper, a collaborative edge computing framework is developed to reduce the computing service latency and improve service reliability for vehicular networks. First, a task partition and scheduling algorithm (TPSA) is proposed to decide the workload allocation and schedule the execution order of the tasks offloaded to the edge servers given a computation offloading strategy. Second, an artificial intelligence (AI) based collaborative computing approach is developed to determine the task offloading, computing, and result delivery policy for vehicles. Specifically, the offloading and computing problem is formulated as a Markov decision process. A deep reinforcement learning technique, i.e., deep deterministic policy gradient, is adopted to find the optimal solution in a complex urban transportation network. By our approach, the service cost, which includes computing service latency and service failure penalty, can be minimized via the optimal workload assignment and server selection in collaborative computing. Simulation results show that the proposed AI-based collaborative computing approach can adapt to a highly dynamic environment with outstanding performance.

eess.SY↗

arXiv2020

Energy-Efficient UAV-Assisted Mobile Edge Computing: Resource Allocation and Trajectory Optimization

In this paper, we study unmanned aerial vehicle (UAV) assisted mobile edge computing (MEC) with the objective to optimize computation offloading with minimum UAV energy consumption. In the considered scenario, a UAV plays the role of an aerial cloudlet to collect and process the computation tasks offloaded by ground users. Given the service requirements of users, we aim to maximize UAV energy efficiency by jointly optimizing the UAV trajectory, the user transmit power, and computation load allocation. The resulting optimization problem corresponds to nonconvex fractional programming, and the Dinkelbach algorithm and the successive convex approximation (SCA) technique are adopted to solve it. Furthermore, we decompose the problem into multiple subproblems for distributed and parallel problem solving. To cope with the case when the knowledge of user mobility is limited, we adopt a spatial distribution estimation technique to predict the location of ground users so that the proposed approach can still be applied. Simulation results demonstrate the effectiveness of the proposed approach for maximizing the energy efficiency of UAV.

cs.NI↗

arXiv2020

Low-Latency and Fresh Content Provision in Information-Centric Vehicular Networks

In this paper, the content service provision of information-centric vehicular networks (ICVNs) is investigated from the aspect of mobile edge caching, considering the dynamic driving-related context information. To provide up-to-date information with low latency, two schemes are designed for cache update and content delivery at the roadside units (RSUs). The roadside unit centric (RSUC) scheme decouples cache update and content delivery through bandwidth splitting, where the cached content items are updated regularly in a round-robin manner. The request adaptive (ReA) scheme updates the cached content items upon user requests with certain probabilities. The performance of both proposed schemes are analyzed, whereby the average age of information (AoI) and service latency are derived in closed forms. Surprisingly, the AoI-latency trade-off does not always exist, and frequent cache update can degrade both performances. Thus, the RSUC and ReA schemes are further optimized to balance the AoI and latency. Extensive simulations are conducted on SUMO and OMNeT++ simulators, and the results show that the proposed schemes can reduce service latency by up to 80\% while guaranteeing content freshness in heavily loaded ICVNs.

cs.NI↗

arXiv2020

Portably parallel construction of a CI wave function from a matrix-product state using the Charm++ framework

The constructions of configuration interaction (CI) expansions from a matrix-product state (MPS) involves numerous matrix operations and the skillful sampling of important configurations when in a huge Hilbert space. In this work, we present an efficient procedure for constructing CI expansions from MPS using the Charm++ parallel programming framework, upon which automatic load balancing and object migration facilities can be employed. This procedure was employed in the MPS-to-CI utility (Moritz et al., J. Chem. Phys. 2007, 126, 224109), sampling-reconstructed complete active space algorithm (SR-CAS, Boguslawski et al., J. Chem. Phys. 2011, 134, 224101) and entanglement-driven genetic algorithm (EDGA, Luo et al., J. Chem. Theory Comput. 2017, 13, 4699-4710). It enhances productivity and allows the sampling programs evolve to their population-expansion versions (e.g., EDGA with population expansion [PE-EDGA]). Examples of 1,2-dioxetanone and firefly dioxetanone anion (FDO-) molecules demonstrated that 1) the procedure could be flexibly employed among various multi-core architectures; 2) the parallel efficiencies could be persistently improved simply by increasing the proportion of asynchronous executions; 3) PE-EDGA could construct a CAS-type CI wave function from a huge Hilbert space, with 0.9952 CI completeness and 96.7% correlation energy via ~1.66x10^6 configurations (only 0.0000028% of the total configurations) of a bi-radical state of FDO- molecule using the full valence active space within a few hours.

physics.comp-ph↗