arXiv subjects

Hao Wu

Publications and source records attributed to Hao Wu.

At least 469 records · Page 26Linked to original sources

arXiv2024

Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware Acceleration

Fiber-optic sensing, especially distributed optical fiber vibration (DVS) sensing, is gaining importance in internet of things (IoT) applications, such as industrial safety monitoring and intrusion detection. Despite their wide application, existing post-processing methods that rely on deep learning models for event recognition in DVS systems face challenges with real-time processing of large sample data volumes, particularly in long-distance applications. To address this issue, we propose to use a four-layer convolutional neural network (CNN) with ResNet as the teacher model for knowledge distillation. This results in a significant improvement in accuracy, from 83.41% to 95.39%, on data from previously untrained environments. Additionally, we propose a novel hardware design based on field-programmable gate arrays (FPGA) to further accelerate model inference. This design replaces multiplication with binary shift operations and quantizes model weights, enabling high parallelism and low latency. Our implementation achieves an inference time of 0.083 ms for a spatial-temporal sample covering a 12.5 m fiber length and 0.256 s time frame. This performance enables real-time signal processing over approximately 38.55 km of fiber, about $2.14\times$ the capability of an Nvidia GTX 4090 GPU. The proposed method greatly enhances the efficiency of vibration pattern recognition, promoting the use of DVS as a smart IoT system. The data and code are available at https://github.com/HUST-IOF/Efficient-DVS.

eess.SY↗

arXiv2024

MM-GEF: Multi-modal representation meet collaborative filtering

In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems. The majority of previous work either focuses on learning effective item representation during modelling user-item interactions, or exploring item-item relationships by analysing multi-modal features. Those methods, however, fail to incorporate the collaborative item-user-item relationships into the multi-modal feature-based item structure. In this work, we propose a graph-based item structure enhancement method MM-GEF: Multi-Modal recommendation with Graph Early-Fusion, which effectively combines the latent item structure underlying multi-modal contents with the collaborative signals. Instead of processing the content feature in different modalities separately, we show that the early-fusion of multi-modal features provides significant improvement. MM-GEF learns refined item representations by injecting structural information obtained from both multi-modal and collaborative signals. Through extensive experiments on four publicly available datasets, we demonstrate systematical improvements of our method over state-of-the-art multi-modal recommendation methods.

cs.IR↗

arXiv2024

Towards Consistent Object Detection via LiDAR-Camera Synergy

As human-machine interaction continues to evolve, the capacity for environmental perception is becoming increasingly crucial. Integrating the two most common types of sensory data, images, and point clouds, can enhance detection accuracy. Currently, there is no existing model capable of detecting an object's position in both point clouds and images while also determining their corresponding relationship. This information is invaluable for human-machine interactions, offering new possibilities for their enhancement. In light of this, this paper introduces an end-to-end Consistency Object Detection (COD) algorithm framework that requires only a single forward inference to simultaneously obtain an object's position in both point clouds and images and establish their correlation. Furthermore, to assess the accuracy of the object correlation between point clouds and images, this paper proposes a new evaluation metric, Consistency Precision (CP). To verify the effectiveness of the proposed framework, an extensive set of experiments has been conducted on the KITTI and DAIR-V2X datasets. The study also explored how the proposed consistency detection method performs on images when the calibration parameters between images and point clouds are disturbed, compared to existing post-processing methods. The experimental results demonstrate that the proposed method exhibits excellent detection performance and robustness, achieving end-to-end consistency detection. The source code will be made publicly available at https://github.com/xifen523/COD.

cs.CV↗

arXiv2024

Dual-Channel Latent Factor Analysis Enhanced Graph Contrastive Learning for Recommendation

Graph Neural Networks (GNNs) are powerful learning methods for recommender systems owing to their robustness in handling complicated user-item interactions. Recently, the integration of contrastive learning with GNNs has demonstrated remarkable performance in recommender systems to handle the issue of highly sparse user-item interaction data. Yet, some available graph contrastive learning (GCL) techniques employ stochastic augmentation, i.e., nodes or edges are randomly perturbed on the user-item bipartite graph to construct contrastive views. Such a stochastic augmentation strategy not only brings noise perturbation but also cannot utilize global collaborative signals effectively. To address it, this study proposes a latent factor analysis (LFA) enhanced GCL approach, named LFA-GCL. Our model exclusively incorporates LFA to implement the unconstrained structural refinement, thereby obtaining an augmented global collaborative graph accurately without introducing noise signals. Experiments on four public datasets show that the proposed LFA-GCL outperforms the state-of-the-art models.

cs.LG↗

arXiv2024

Vision Learners Meet Web Image-Text Pairs

Many self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data. First, we conduct a benchmark study of representative self-supervised pre-training methods on large-scale web data in a like-for-like setting. We compare a range of methods, including single-modal ones that use masked training objectives and multi-modal ones that use image-text constrastive training. We observe that existing multi-modal methods do not outperform their single-modal counterparts on vision transfer learning tasks. We derive an information-theoretical view to explain these benchmark results, which provides insight into how to design a novel vision learner. Inspired by this insight, we present a new visual representation pre-training method, MUlti-modal Generator~(MUG), that learns from scalable web sourced image-text data. MUG achieves state-of-the-art transfer performance on a variety of tasks and demonstrates promising scaling properties. Pre-trained models and code will be made public upon acceptance.

cs.CV↗

arXiv2024

Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learning

Dynamic graphs (DG) are often used to describe evolving interactions between nodes in real-world applications. Temporal patterns are a natural feature of DGs and are also key to representation learning. However, existing dynamic GCN models are mostly composed of static GCNs and sequence modules, which results in the separation of spatiotemporal information and cannot effectively capture complex temporal patterns in DGs. To address this problem, this study proposes a spatial-temporal graph convolutional networks with diversified transformation (STGCNDT), which includes three aspects: a) constructing a unified graph tensor convolutional network (GTCN) using tensor M-products without the need to represent spatiotemporal information separately; b) introducing three transformation schemes in GTCN to model complex temporal patterns to aggregate temporal information; and c) constructing an ensemble of diversified transformation schemes to obtain higher representation capabilities. Empirical studies on four DGs that appear in communication networks show that the proposed STGCNDT significantly outperforms state-of-the-art models in solving link weight estimation tasks due to the diversified transformations.

cs.LG↗

arXiv2024

Above-room-temperature intrinsic ferromagnetism in ultrathin van der Waals crystal Fe$_{3+x}$GaTe$_2$

Two-dimensional (2D) van der Waals (vdW) magnets are crucial for ultra-compact spintronics. However, so far, no vdW crystal has exhibited tunable above-room-temperature intrinsic ferromagnetism in the 2D ultrathin regime. Here, we report the tunable above-room-temperature intrinsic ferromagnetism in ultrathin vdW crystal Fe$_{3+x}$GaTe$_2$ ($x$ = 0 and 0.3). By increasing the Fe content, the Curie temperature (TC) and room-temperature saturation magnetization of bulk Fe$_{3+x}$GaTe$_2$ crystals are enhanced from 354 to 376 K and 43.9 to 50.4 emu/g, respectively. Remarkably, the robust anomalous Hall effect in 3-nm Fe$_{3.3}$GaTe$_2$ indicate a record-high TC of 340 K and a large room-temperature perpendicular magnetic anisotropy energy of 6.6 * 10^5 J/m$^3$, superior to other ultrathin vdW ferromagnets. First-principles calculations reveal the asymmetric density of states and an additional large spin exchange interaction in ultrathin Fe$_{3+x}$GaTe$_2$ responsible for robust intrinsic ferromagnetism and higher Tc. This work opens a window for above-room-temperature ultrathin 2D magnets in vdW-integrated spintronics.

cond-mat.mtrl-sci↗

arXiv2024

Rényi--Sobolev Inequalities and Connections to Spectral Graph Theory

In this paper, we generalize the log-Sobolev inequalities to Rényi--Sobolev inequalities by replacing the entropy with the two-parameter entropy, which is a generalized version of entropy and closely related to Rényi divergences. We derive the sharp nonlinear dimension-free version of this kind of inequalities. Interestingly, the resultant inequalities show a transition phenomenon depending on the parameters. We then connect Rényi--Sobolev inequalities to contractive and data-processing inequalities, concentration inequalities, and spectral graph theory. Our proofs in this paper are based on the information-theoretic characterization of the Rényi--Sobolev inequalities, as well as the method of types.

math.PR↗

arXiv2024

MNTD: An Efficient Dynamic Community Detector Based on Nonnegative Tensor Decomposition

Dynamic community detection is crucial for elucidating the temporal evolution of social structures, information dissemination, and interactive behaviors within complex networks. Nonnegative matrix factorization provides an efficient framework for identifying communities in static networks but fall short in depicting temporal variations in community affiliations. To solve this problem, this paper proposes a Modularity maximization-incorporated Nonnegative Tensor RESCAL Decomposition (MNTD) model for dynamic community detection. This method serves two primary functions: a) Nonnegative tensor RESCAL decomposition extracts latent community structures in different time slots, highlighting the persistence and transformation of communities; and b) Incorporating an initial community structure into the modularity maximization algorithm, facilitating more precise community segmentations. Comparative analysis of real-world datasets shows that the MNTD is superior to state-of-the-art dynamic community detection methods in the accuracy of community detection.

cs.SI↗

arXiv2024

A Probabilistic Approach for Queue Length Estimation Using License Plate Recognition Data: Considering Overtaking in Multi-lane Scenarios

Multi-section license plate recognition (LPR) data provides input-output information and sampled travel times of the investigated link, serving as an ideal data source for lane-based queue length estimation in recent studies. However, most of these studies assumed the strict FIFO rule or a specific arrival process, thus ignoring the potential impact of overtaking and the variation of traffic flows, especially in multi-lane scenarios. To address this issue, we propose a probabilistic approach to derive the stochastic queue length by constructing a conditional probability model of no-delay arrival time (NAT), i.e., the arrival time of vehicles without experiencing any delay, based on multi-section LPR data. First, the NAT conditions for all vehicles are established based on upstream and downstream vehicle departure times and sequences. To reduce the computational dimensionality and complexity, a DP-based algorithm is developed for vehicle group partitioning based on potential interactions between vehicles. Then, the conditional probability of NATs of each vehicle group is derived and an MCMC sampling method is employed for calculation. Subsequently, the stochastic queue profile and maximum queue length for each cycle can be derived based on the NATs of vehicles. Eventually, to leverage the LPR data sufficiently, we extend our approach to multi-lane scenarios, where the problem can be converted to a weighted general exact coverage problem and solved by a backtracking algorithm with heuristics. Empirical and simulation experiments have shown that the proposed approach outperforms the state-of-the-art method, demonstrating significant improvements in accuracy and robustness across various traffic conditions, including different V/C ratios, matching rates, and FIFO violation rates. In addition, the performance of the proposed approach can be further improved by utilizing multi-lane LPR data.

eess.SP↗

arXiv2024

Speed of random walk on dynamical percolation in nonamenable transitive graphs

Let $G$ be a nonamenable transitive unimodular graph. In dynamical percolation, every edge in $G$ refreshes its status at rate $μ>0$, and following the refresh, each edge is open independently with probability $p$. The random walk traverses $G$ only along open edges, moving at rate $1$. In the critical regime $p=p_c$, we prove that the speed of the random walk is at most $O(\sqrt{μ\log(1/μ)})$, provided that $μ\le e^{-1}$. In the supercritical regime $p>p_c$, we prove that the speed on $G$ is of order 1 (uniformly in $μ)$, while in the subcritical regime $p<p_c$, the speed is of order $μ\wedge 1$.

math.PR↗

arXiv2024

Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning

Forensic pathology is critical in determining the cause and manner of death through post-mortem examinations, both macroscopic and microscopic. The field, however, grapples with issues such as outcome variability, laborious processes, and a scarcity of trained professionals. This paper presents SongCi, an innovative visual-language model (VLM) designed specifically for forensic pathology. SongCi utilizes advanced prototypical cross-modal self-supervised contrastive learning to enhance the accuracy, efficiency, and generalizability of forensic analyses. It was pre-trained and evaluated on a comprehensive multi-center dataset, which includes over 16 million high-resolution image patches, 2,228 vision-language pairs of post-mortem whole slide images (WSIs), and corresponding gross key findings, along with 471 distinct diagnostic outcomes. Our findings indicate that SongCi surpasses existing multi-modal AI models in many forensic pathology tasks, performs comparably to experienced forensic pathologists and significantly better than less experienced ones, and provides detailed multi-modal explainability, offering critical assistance in forensic investigations. To the best of our knowledge, SongCi is the first VLM specifically developed for forensic pathological analysis and the first large-vocabulary computational pathology (CPath) model that directly processes gigapixel WSIs in forensic science.

eess.IV↗

arXiv2024

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate "hallucinated" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they only evaluate the performance of the LLM component of the RAG pipeline in the experiments, and neglect the influence of the retrieval component and the external knowledge database. To address these issues, this paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios. Specifically, we have categorized the range of RAG applications into four distinct types-Create, Read, Update, and Delete (CRUD), each representing a unique use case. "Create" refers to scenarios requiring the generation of original, varied content. "Read" involves responding to intricate questions in knowledge-intensive situations. "Update" focuses on revising and rectifying inaccuracies or inconsistencies in pre-existing texts. "Delete" pertains to the task of summarizing extensive texts into more concise forms. For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems. We also analyze the effects of various components of the RAG system, such as the retriever, the context length, the knowledge base construction, and the LLM. Finally, we provide useful insights for optimizing the RAG technology for different scenarios.

cs.CL↗

arXiv2024

Nematic Bogoliubov Fermi surfaces from magnetic toroidal order in FeSe$_{1-x}$S$_x$

Recently it has been argued that the superconducting state of FeSe$_{1-x}$S$_x$ exhibits Bogoliubov Fermi surfaces for $x>0.17$. These Bogoliubov Fermi surfaces appear together with broken time-reversal symmetry and surprisingly demonstrate nematic behavior in a structurally tetragonal phase. Through a symmetry-based analysis of Bogoliubov Fermi surfaces that can arise from broken time-reversal symmetry, we argue that the likely origin of time-reversal symmetry breaking is due to magnetic toroidal order. We show that this magnetic toroidal order naturally appears as a consequence of either static Néel antiferromagnetic order or due to the formation of a spontaneous pair density wave superconducting order. Finally, we reveal that independent of the presence of Bogoliubov Fermi surfaces, supercurrents will induce Néel magnetic order in many Fe-based superconductors.

cond-mat.supr-con↗

arXiv2024

On Completeness of SDP-Based Barrier Certificate Synthesis over Unbounded Domains

Barrier certificates, serving as differential invariants that witness system safety, play a crucial role in the verification of cyber-physical systems (CPS). Prevailing computational methods for synthesizing barrier certificates are based on semidefinite programming (SDP) by exploiting Putinar Positivstellensatz. Consequently, these approaches are limited by the Archimedean condition, which requires all variables to be bounded, i.e., systems are defined over bounded domains. For systems over unbounded domains, unfortunately, existing methods become incomplete and may fail to identify potential barrier certificates. In this paper, we address this limitation for the unbounded cases. We first give a complete characterization of polynomial barrier certificates by using homogenization, a recent technique in the optimization community to reduce an unbounded optimization problem to a bounded one. Furthermore, motivated by this formulation, we introduce the definition of homogenized systems and propose a complete characterization of a family of non-polynomial barrier certificates with more expressive power. Experimental results demonstrate that our two approaches are more effective while maintaining a comparable level of efficiency.

eess.SY↗

arXiv2024

Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum

Graph-based fraud detection (GFD) can be regarded as a challenging semi-supervised node binary classification task. In recent years, Graph Neural Networks (GNN) have been widely applied to GFD, characterizing the anomalous possibility of a node by aggregating neighbor information. However, fraud graphs are inherently heterophilic, thus most of GNNs perform poorly due to their assumption of homophily. In addition, due to the existence of heterophily and class imbalance problem, the existing models do not fully utilize the precious node label information. To address the above issues, this paper proposes a semi-supervised GNN-based fraud detector SEC-GFD. This detector includes a hybrid filtering module and a local environmental constraint module, the two modules are utilized to solve heterophily and label utilization problem respectively. The first module starts from the perspective of the spectral domain, and solves the heterophily problem to a certain extent. Specifically, it divides the spectrum into various mixed-frequency bands based on the correlation between spectrum energy distribution and heterophily. Then in order to make full use of the node label information, a local environmental constraint module is adaptively designed. The comprehensive experimental results on four real-world fraud detection datasets denote that SEC-GFD outperforms other competitive graph-based fraud detectors. We release our code at https://github.com/Sunxkissed/SEC-GFD.

cs.LG↗

arXiv2024

GLADformer: A Mixed Perspective for Graph-level Anomaly Detection

Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph dataset. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most contemporary methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level anomaly detector namely GLADformer, consisting of two key modules. Specifically, we first design a Graph Transformer module with global spectrum enhancement, which ensures balanced and resilient parameter distributions by fusing global features and spectral distribution characteristics. Furthermore, to uncover local anomalous attributes, we customize a band-pass spectral GNN message passing module that further enhances the model's generalization capability. Through comprehensive experiments on ten real-world datasets from multiple domains, we validate the effectiveness and robustness of GLADformer. This demonstrates that GLADformer outperforms current state-of-the-art models in graph-level anomaly detection, particularly in effectively capturing global anomaly representations and spectral characteristics.

cs.LG↗

arXiv2024

Separation property and asymptotic behavior for a transmission problem of the bulk-surface coupled Cahn-Hilliard system with singular potentials and its Robin approximation

We consider a class of bulk-surface coupled Cahn-Hilliard systems in a smooth, bounded domain $Ω\subset\mathbb{R}^{d}$ $(d\in\{2,3\})$, where the trace value of the bulk phase variable is connected to the surface phase variable via a Dirichlet boundary condition or its Robin approximation. For a general class of singular potentials (including the physically relevant logarithmic potential), we establish the regularity propagation of global weak solutions to the initial boundary value problem. In particular, when the spatial dimension is two, we prove the instantaneous strict separation property, which ensures that every global weak solution remains uniformly away from the pure states $\pm 1$ after any given positive time. In the three-dimensional case, we obtain the eventual strict separation property that holds for sufficiently large time. This strict separation property allows us to prove that every global weak solution converges to a single equilibrium as time goes to infinity using the Łojasiewicz-Simon approach. Finally, we study the double obstacle limit for the problem with logarithmic potentials in the bulk and on the boundary, showing that as the absolute temperature $Θ$ tends to zero, the corresponding weak solutions converge (for a suitable subsequence) to a weak solution of the problem with a double obstacle potential.

math.AP↗