arXiv subjects

Ying Zhang

Publications and source records attributed to Ying Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2025

Efficient Learning-based Graph Simulation for Temporal Graphs

Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal graphs). While most of the existing graph generators focus on static graphs, the temporal information of the graphs is ignored. In this paper, we focus on simulating temporal graphs, which aim to reproduce the structural and temporal properties of the observed real-life temporal graphs. In this paper, we first give an overview of the existing temporal graph generators, including recently emerged learning-based approaches. Most of these learning-based methods suffer from one of the limitations: low efficiency in training or slow generating, especially for temporal random walk-based methods. Therefore, we propose an efficient learning-based approach to generate graph snapshots, namely temporal graph autoencoder (TGAE). Specifically, we propose an attention-based graph encoder to encode temporal and structural characteristics on sampled ego-graphs. And we proposed an ego-graph decoder that can achieve a good trade-off between simulation quality and efficiency in temporal graph generation. Finally, the experimental evaluation is conducted among our proposed TGAE and representative temporal graph generators on real-life temporal graphs and synthesized graphs. It is reported that our proposed approach outperforms the state-of-the-art temporal graph generators by means of simulation quality and efficiency.

cs.LG↗

arXiv2025

Closing the Loop: Coordinating Inventory and Recommendation via Deep Reinforcement Learning on Multiple Timescales

Effective cross-functional coordination is essential for enhancing firm-wide profitability, particularly in the face of growing organizational complexity and scale. Recent advances in artificial intelligence, especially in reinforcement learning (RL), offer promising avenues to address this fundamental challenge. This paper proposes a unified multi-agent RL framework tailored for joint optimization across distinct functional modules, exemplified via coordinating inventory replenishment and personalized product recommendation. We first develop an integrated theoretical model to capture the intricate interplay between these functions and derive analytical benchmarks that characterize optimal coordination. The analysis reveals synchronized adjustment patterns across products and over time, highlighting the importance of coordinated decision-making. Leveraging these insights, we design a novel multi-timescale multi-agent RL architecture that decomposes policy components according to departmental functions and assigns distinct learning speeds based on task complexity and responsiveness. Our model-free multi-agent design improves scalability and deployment flexibility, while multi-timescale updates enhance convergence stability and adaptability across heterogeneous decisions. We further establish the asymptotic convergence of the proposed algorithm. Extensive simulation experiments demonstrate that the proposed approach significantly improves profitability relative to siloed decision-making frameworks, while the behaviors of the trained RL agents align closely with the managerial insights from our theoretical model. Taken together, this work provides a scalable, interpretable RL-based solution to enable effective cross-functional coordination in complex business settings.

cs.AI↗

arXiv2025

Optimal Smooth Coverage Trajectory Planning for Quadrotors in Cluttered Environment

For typical applications of UAVs in power grid scenarios, we construct the problem as planning UAV trajectories for coverage in cluttered environments. In this paper, we propose an optimal smooth coverage trajectory planning algorithm. The algorithm consists of two stages. In the front-end, a Genetic Algorithm (GA) is employed to solve the Traveling Salesman Problem (TSP) for Points of Interest (POIs), generating an initial sequence of optimized visiting points. In the back-end, the sequence is further optimized by considering trajectory smoothness, time consumption, and obstacle avoidance. This is formulated as a nonlinear least squares problem and solved to produce a smooth coverage trajectory that satisfies these constraints. Numerical simulations validate the effectiveness of the proposed algorithm, ensuring UAVs can smoothly cover all POIs in cluttered environments.

cs.RO↗

arXiv2025

DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning

Deep graph models have achieved great success in network representation learning. However, their focus on pairwise relationships restricts their ability to learn pervasive higher-order interactions in real-world systems, which can be naturally modeled as hypergraphs. To tackle this issue, Hypergraph Neural Networks (HNNs) have garnered substantial attention in recent years. Despite the proposal of numerous HNNs, the absence of consistent experimental protocols and multi-dimensional empirical analysis impedes deeper understanding and further development of HNN research. While several toolkits for deep hypergraph learning (DHGL) have been introduced to facilitate algorithm evaluation, they provide only limited quantitative evaluation results and insufficient coverage of advanced algorithms, datasets, and benchmark tasks. To fill the gap, we introduce DHG-Bench, the first comprehensive benchmark for HNNs. Specifically, DHG-Bench systematically investigates the characteristics of HNNs in terms of four dimensions: effectiveness, efficiency, robustness, and fairness. We comprehensively evaluate 17 state-of-the-art HNN algorithms on 22 diverse datasets spanning node-, edge-, and graph-level tasks, under unified experimental settings. Extensive experiments reveal both the strengths and limitations of existing algorithms, offering valuable insights and directions for future research. Furthermore, to facilitate reproducible research, we have developed an easy-to-use library for training and evaluating different HNN methods. The DHG-Bench library is available at: https://github.com/Coco-Hut/DHG-Bench.

cs.LG↗

arXiv2025

When Life Paths Cross: Extracting Human Interactions in Time and Space from Wikipedia

Interactions among notable individuals -- whether examined individually, in groups, or as networks -- often convey significant messages across cultural, economic, political, scientific, and historical perspectives. By analyzing the times and locations of these interactions, we can observe how dynamics unfold across regions over time. However, relevant studies are often constrained by data scarcity, particularly concerning the availability of specific location and time information. To address this issue, we mine millions of biography pages from Wikipedia, extracting 685,966 interaction records in the form of (Person1, Person2, Time, Location) interaction quadruplets. The key elements of these interactions are often scattered throughout the heterogeneous crowd-sourced text and may be loosely or indirectly associated. We overcome this challenge by designing a model that integrates attention mechanisms, multi-task learning, and feature transfer methods, achieving an F1 score of 86.51%, which outperforms baseline models. We further conduct an empirical analysis of intra- and inter-party interactions among political figures to examine political polarization in the US, showcasing the potential of the extracted data from a perspective that may not be possible without this data. We make our code, the extracted interaction data, and the WikiInteraction dataset of 4,507 labeled interaction quadruplets publicly available.

cs.SI↗

arXiv2025

USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model

Recently, Large Language Models (LLMs) have been widely employed in Conversational Recommender Systems (CRSs). Unlike traditional language model approaches that focus on training, all existing LLMs-based approaches are mainly centered around how to leverage the summarization and analysis capabilities of LLMs while ignoring the issue of training. Therefore, in this work, we propose an integrated training-inference framework, User-Simulator-Based framework (USB-Rec), for improving the performance of LLMs in conversational recommendation at the model level. Firstly, we design a LLM-based Preference Optimization (PO) dataset construction strategy for RL training, which helps the LLMs understand the strategies and methods in conversational recommendation. Secondly, we propose a Self-Enhancement Strategy (SES) at the inference stage to further exploit the conversational recommendation potential obtained from RL training. Extensive experiments on various datasets demonstrate that our method consistently outperforms previous state-of-the-art methods.

cs.CL↗

arXiv2025

Impact of Solar Integration on Grid Security: Unveiling Vulnerabilities in Load Redistribution Attacks

Load redistribution (LR) attacks represent a practical and sophisticated form of false data injection (FDI) attacks, where the attacker manipulates grid data to influence economic operations of the grid through misleading security constrained economic dispatch (SCED) decisions. Traditionally, LR attack models operate under the assumption that generator measurements are secure and immune to tampering. However, the increasing integration of solar generation into power grids challenges this assumption, exposing new vulnerabilities. This paper proposes an enhanced load redistribution attack model, addressing new vulnerabilities introduced by the increasing integration of solar generation in power grids. The study demonstrates that manipulating solar generation data significantly disrupts grid economics, with peak impacts during periods of high solar generation.

eess.SY↗

arXiv2025

MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training

Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named experts, on a per-token basis. This gated computation generates dynamic communications that cannot be determined beforehand, challenging the existing GPU interconnects that remain static during the distributed training process. In this paper, we advocate for a first-of-its-kind system, called MixNet, that unlocks topology reconfiguration during distributed MoE training. Towards this vision, we first perform a production measurement study and show that the MoE dynamic communication pattern has strong locality, alleviating the requirement of global reconfiguration. Based on this, we design and implement a regionally reconfigurable high-bandwidth domain on top of existing electrical interconnects using optical circuit switching (OCS), achieving scalability while maintaining rapid adaptability. We have built a fully functional MixNet prototype with commodity hardware and a customized collective communication runtime that trains state-of-the-art MoE models with in-training topology reconfiguration across 32 A100 GPUs. Large-scale packet-level simulations show that MixNet delivers comparable performance as the non-blocking fat-tree fabric while boosting the training cost efficiency (e.g., performance per dollar) of four representative MoE models by 1.2x-1.5x and 1.9x-2.3x at 100 Gbps and 400 Gbps link bandwidths, respectively.

cs.NI↗

arXiv2025

The equation of state for neutron stars with speed of sound constraints via Bayesian inference

The parametrized equation of state (EOS) of neutron stars is investigated by Bayesian inference method with various constraints from both nuclear physics and modern astronomical observations. The expansion coefficients correspond to the properties of symmetric nuclear matter and the density dependence of the symmetry energy. The empirical values of the symmetry energy at subsaturation density and the density of crust-core phase transition are considered to limit the low-density behavior of EOS, i.e. $L_{\mathrm{sym}} $, while the speed of sound of neutron star matter and mass-radius observations of millisecond pulsars PSR J0030+0451 and PSR J0740+6620 are adopted to eliminate the high-order expansion coefficients, such as $Q_{\mathrm{sat}}$ and $Q_{\mathrm{sym}} $. Finally, our analysis reveals that the skewness coefficient $Q_{\mathrm{sat}}$ of the energy per nucleon in symmetric nuclear matter (SNM) exhibits the strongest correlation with the speed of sound, constrained to $Q_{\mathrm{sat}} = -69.50_{-31.93}^{+16.52} \, \mathrm{MeV}$, whose uncertainties are much smaller than those of the experiments of heavy-ion collisions. The symmetry energy parameters are determined as follows: slope $L_{\mathrm{sym}} = 34.32_{-11.85}^{+13.66} \, \mathrm{MeV}$, curvature $K_{\mathrm{sym}} = -58.45_{-89.46}^{+88.47} \, \mathrm{MeV}$, and skewness $Q_{\mathrm{sym}} = 302.28_{-231.89}^{+251.62} \, \mathrm{MeV}$. Additionally, the radii of canonical ($1.4 \, M_{\odot}$) and massive ($2.0 \, M_{\odot}$) neutron stars are predicted as $R_{1.4} = 11.85_{-0.15}^{+0.06} \, \text{km}$ and $R_{2.0} = 11.42_{-0.35}^{+0.23} \, \text{km}$, respectively, with a maximum mass of $M_{\mathrm{max}} = 2.12_{-0.05}^{+0.11} \, M_{\odot}$. The tidal deformability is $Λ_{1.4} = 303.57_{-45.22}^{+47.95}$ at $1.4 \, M_\odot$, which is consistent with the analysis of the GW170817 event.

nucl-th↗

arXiv2025

Behavioral Fingerprinting of Large Language Models

Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them. This paper introduces a novel ``Behavioral Fingerprinting'' framework designed to move beyond traditional evaluation by creating a multi-faceted profile of a model's intrinsic cognitive and interactive styles. Using a curated \textit{Diagnostic Prompt Suite} and an innovative, automated evaluation pipeline where a powerful LLM acts as an impartial judge, we analyze eighteen models across capability tiers. Our results reveal a critical divergence in the LLM landscape: while core capabilities like abstract and causal reasoning are converging among top models, alignment-related behaviors such as sycophancy and semantic robustness vary dramatically. We further document a cross-model default persona clustering (ISTJ/ESTJ) that likely reflects common alignment incentives. Taken together, this suggests that a model's interactive nature is not an emergent property of its scale or reasoning power, but a direct consequence of specific, and highly variable, developer alignment strategies. Our framework provides a reproducible and scalable methodology for uncovering these deep behavioral differences. Project: https://github.com/JarvisPei/Behavioral-Fingerprinting

cs.CL↗

arXiv2025

Triangle Counting in Hypergraph Streams: A Complete and Practical Approach

Triangle counting in hypergraph streams, including both hyper-vertex and hyper-edge triangles, is a fundamental problem in hypergraph analytics, with broad applications. However, existing methods face two key limitations: (i) an incomplete classification of hyper-vertex triangle structures, typically considering only inner or outer triangles; and (ii) inflexible sampling schemes that predefine the number of sampled hyperedges, which is impractical under strict memory constraints due to highly variable hyperedge sizes. To address these challenges, we first introduce a complete classification of hyper-vertex triangles, including inner, hybrid, and outer triangles. Based on this, we develop HTCount, a reservoir-based algorithm that dynamically adjusts the sample size based on the available memory M. To further improve memory utilization and reduce estimation error, we develop HTCount-P, a partition-based variant that adaptively partitions unused memory into independent sample subsets. We provide theoretical analysis of the unbiasedness and variance bounds of the proposed algorithms. Case studies demonstrate the expressiveness of our triangle structures in revealing meaningful interaction patterns. Extensive experiments on real-world hypergraphs show that both our algorithms achieve highly accurate triangle count estimates under strict memory constraints, with relative errors that are 1 to 2 orders of magnitude lower than those of existing methods and consistently high throughput.

cs.DS↗

arXiv2025

A Deep Learning Framework for Joint Channel Acquisition and Communication Optimization in Movable Antenna Systems

This paper presents an end-to-end deep learning framework in a movable antenna (MA)-enabled multiuser communication system. In contrast to the conventional works assuming perfect channel state information (CSI), we address the practical CSI acquisition issue through the design of pilot signals and quantized CSI feedback, and further incorporate the joint optimization of channel estimation, MA placement, and precoding design. The proposed mechanism enables the system to learn an optimized transmission strategy from imperfect channel data, overcoming the limitations of conventional methods that conduct channel estimation and antenna position optimization separately. To balance the performance and overhead, we further extend the proposed framework to optimize the antenna placement based on the statistical CSI. Simulation results demonstrate that the proposed approach consistently outperforms traditional benchmarks in terms of achievable sum-rate of users, especially under limited feedback and sparse channel environments. Notably, it achieves a performance comparable to the widely-adopted gradient-based methods with perfect CSI, while maintaining significantly lower CSI feedback overhead. These results highlight the effectiveness and adaptability of learning-based MA system design for future wireless systems.

cs.IT↗

arXiv2025

Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring

Single image defocus deblurring aims to recover an all-in-focus image from a defocus counterpart, where accurately modeling spatially varying blur kernels remains a key challenge. Most existing methods rely on spatial features for kernel estimation, but their performance degrades in severely blurry regions where local high-frequency details are missing. To address this, we propose a Frequency-Driven Inverse Kernel Prediction network (FDIKP) that incorporates frequency-domain representations to enhance structural identifiability in kernel modeling. Given the superior discriminative capability of the frequency domain for blur modeling, we design a Dual-Branch Inverse Kernel Prediction (DIKP) strategy that improves the accuracy of kernel estimation while maintaining stability. Moreover, considering the limited number of predicted inverse kernels, we introduce a Position Adaptive Convolution (PAC) to enhance the adaptability of the deconvolution process. Finally, we propose a Dual-Domain Scale Recurrent Module (DSRM) to fuse deconvolution results and progressively improve deblurring quality from coarse to fine. Extensive experiments demonstrate that our method outperforms existing approaches. Code will be made publicly available.

cs.CV↗

arXiv2025

RMSL: Weakly-Supervised Insider Threat Detection with Robust Multi-sphere Learning

Insider threat detection aims to identify malicious user behavior by analyzing logs that record user interactions. Due to the lack of fine-grained behavior-level annotations, detecting specific behavior-level anomalies within user behavior sequences is challenging. Unsupervised methods face high false positive rates and miss rates due to the inherent ambiguity between normal and anomalous behaviors. In this work, we instead introduce weak labels of behavior sequences, which have lower annotation costs, i.e., the training labels (anomalous or normal) are at sequence-level instead of behavior-level, to enhance the detection capability for behavior-level anomalies by learning discriminative features. To achieve this, we propose a novel framework called Robust Multi-sphere Learning (RMSL). RMSL uses multiple hyper-spheres to represent the normal patterns of behaviors. Initially, a one-class classifier is constructed as a good anomaly-supervision-free starting point. Building on this, using multiple instance learning and adaptive behavior-level self-training debiasing based on model prediction confidence, the framework further refines hyper-spheres and feature representations using weak sequence-level labels. This approach enhances the model's ability to distinguish between normal and anomalous behaviors. Extensive experiments demonstrate that RMSL significantly improves the performance of behavior-level insider threat detection.

cs.CR↗

arXiv2025

Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms

In this paper, we propose two new algorithms, namely, aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in Wasserstein-1 and Wasserstein-2 distances with rates of convergence equal to $1+q/2$ and $1/2+q/4$, respectively, under a local Hölder condition with exponent $q\in(0,1]$ and a convexity at infinity condition on the potential of the target distribution. Similar results are obtained for aHOLLA under certain global continuity conditions and a dissipativity condition. Crucially, we achieve state-of-the-art rates of convergence of the proposed algorithms in the non-convex setting which are higher than those of the existing algorithms. Examples from high-dimensional sampling and logistic regression are presented, and numerical results support our main findings.

math.ST↗

arXiv2025

Understanding the low-lying $Ω_c$ structures from a coupled-channel perspective

We perform a systematic analysis of the low-lying $Ω_c$ structures in a coupled-channel approach. The couplings between meson-baryon channels, $Ξ_c \bar K$, $Ξ_c^{\prime} \bar K$, $Ξ_c^{*} \bar K$, $Ω_cη$ and $Ω_c^{*}η$, and three-quark bare states $Ω_c(1P_λ)$ are considered. We predict a bound state $Ω_c(2954)$ below the $Ξ_c \bar K$ threshold with $(J^P,j)=(1/2^-,0)$, which can be studied in the final states of $Ω_c^{(*)} π$ and $Ω_c^{(*)} γ$. Also, the resonances $Ω_c(3000)$ and $Ω_c(3050)$ can be classified as the lower $(J^P,j)=(1/2^-,1)$ and $(J^P,j)=(3/2^-,1)$ states, respectively. Our present assignments based on this coupled-channel perspective are significantly different from those of traditional three-quark picture and of molecular scenario. The future BelleII and LHCb experiments can search for the bound state $Ω_c(2954)$ and measure the spin-parities of particles $Ω_c(3000)$ and $Ω_c(3050)$ to test our predictions.

hep-ph↗

arXiv2025

Empowering Tabular Data Preparation with Language Models: Why and How?

Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing the intricate relationships within tables and adapting to the tasks involved. Recent advances in Language Models (LMs), especially in Large Language Models (LLMs), offer new opportunities to automate and support tabular data preparation. However, why LMs suit tabular data preparation (i.e., how their capabilities match task demands) and how to use them effectively across phases still remain to be systematically explored. In this survey, we systematically analyze the role of LMs in enhancing tabular data preparation processes, focusing on four core phases: data acquisition, integration, cleaning, and transformation. For each phase, we present an integrated analysis of how LMs can be combined with other components for different preparation tasks, highlight key advancements, and outline prospective pipelines.

cs.AI↗

arXiv2025

Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches, both of which encode textual attributes and temporal structures for DyTAG representation. We observe that DyTAGs inherently comprise three distinct modalities: temporal, textual, and structural, often exhibiting completely disjoint distributions. However, the first two modalities are largely overlooked by existing studies, leading to suboptimal performance. To address this, we propose MoMent, a multi-modal model that explicitly models, integrates, and aligns each modality to learn node representations for link prediction. Given the disjoint nature of the original modality distributions, we first construct modality-specific features and encode them using individual encoders to capture correlations across temporal patterns, semantic context, and local structures. Each encoder generates modality-specific tokens, which are then fused into comprehensive node representations with a theoretical guarantee. To avoid disjoint subspaces of these heterogeneous modalities, we propose a dual-domain alignment loss that first aligns their distributions globally and then fine-tunes coherence at the instance level. This enhances coherent representations from temporal, textual, and structural views. Extensive experiments across seven datasets show that MoMent achieves up to 17.28% accuracy improvement and up to 31x speed-up against eight baselines.

cs.LG↗