arXiv subjects

Sibo Wang

Publications and source records attributed to Sibo Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision

Graph-level anomaly detection (GAD) is critical in diverse domains such as drug discovery, yet high labeling costs and dataset imbalance hamper the performance of Graph Neural Networks (GNNs). To address these issues, we propose FracAug, an innovative plug-in augmentation framework that enhances GNNs by generating semantically consistent graph variants and pseudo-labeling with mutual verification. Unlike previous heuristic methods, FracAug learns semantics within given graphs and synthesizes fractional variants, guided by a novel weighted distance-aware margin loss. This captures multi-scale topology to generate diverse, semantic-preserving graphs unaffected by data imbalance. Then, FracAug utilizes predictions from both original and augmented graphs to pseudo-label unlabeled data, iteratively expanding the training set. As a model-agnostic module compatible with various GNNs, FracAug demonstrates remarkable universality and efficacy: experiments across 14 GNNs on 12 real-world datasets show consistent gains, boosting average AUROC, AUPRC, and F1-score by up to 5.72%, 7.23%, and 4.18%, respectively.

cs.LG↗

arXiv2025

Collaborative Evolution of Intelligent Agents in Large-Scale Microservice Systems

This paper proposes an intelligent service optimization method based on a multi-agent collaborative evolution mechanism to address governance challenges in large-scale microservice architectures. These challenges include complex service dependencies, dynamic topology structures, and fluctuating workloads. The method models each service as an agent and introduces graph representation learning to construct a service dependency graph. This enables agents to perceive and embed structural changes within the system. Each agent learns its policy based on a Markov Decision Process. A centralized training and decentralized execution framework is used to integrate local autonomy with global coordination. To enhance overall system performance and adaptability, a game-driven policy optimization mechanism is designed. Through a selection-mutation process, agent strategy distributions are dynamically adjusted. This supports adaptive collaboration and behavioral evolution among services. Under this mechanism, the system can quickly respond and achieve stable policy convergence when facing scenarios such as sudden workload spikes, topology reconfigurations, or resource conflicts. To evaluate the effectiveness of the proposed method, experiments are conducted on a representative microservice simulation platform. Comparative analyses are performed against several advanced approaches, focusing on coordination efficiency, adaptability, and policy convergence performance. Experimental results show that the proposed method outperforms others in several key metrics. It significantly improves governance efficiency and operational stability in large-scale microservice systems. The method demonstrates strong practical value and engineering feasibility.

cs.DC↗

arXiv2025

Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services

This study proposes an anomaly detection method based on the Transformer architecture with integrated multiscale feature perception, aiming to address the limitations of temporal modeling and scale-aware feature representation in cloud service environments. The method first employs an improved Transformer module to perform temporal modeling on high-dimensional monitoring data, using a self-attention mechanism to capture long-range dependencies and contextual semantics. Then, a multiscale feature construction path is introduced to extract temporal features at different granularities through downsampling and parallel encoding. An attention-weighted fusion module is designed to dynamically adjust the contribution of each scale to the final decision, enhancing the model's robustness in anomaly pattern modeling. In the input modeling stage, standardized multidimensional time series are constructed, covering core signals such as CPU utilization, memory usage, and task scheduling states, while positional encoding is used to strengthen the model's temporal awareness. A systematic experimental setup is designed to evaluate performance, including comparative experiments and hyperparameter sensitivity analysis, focusing on the impact of optimizers, learning rates, anomaly ratios, and noise levels. Experimental results show that the proposed method outperforms mainstream baseline models in key metrics, including precision, recall, AUC, and F1-score, and maintains strong stability and detection performance under various perturbation conditions, demonstrating its superior capability in complex cloud environments.

cs.LG↗

arXiv2025

Efficient Integration of Multi-View Attributed Graphs for Clustering and Embedding

A multi-view attributed graph (MVAG) G captures the diverse relationships and properties of real-world entities through multiple graph views and attribute views. Effectively utilizing all views in G is essential for MVAG clustering and embedding, which are important for applications like recommendation systems, anomaly detection, social network analysis, etc. Existing methods either achieve inferior result quality or incur significant computational costs to handle large-scale MVAGs. In this paper, we present a spectrum-guided Laplacian aggregation scheme with an effective objective formulation and two efficient algorithms SGLA and SGLA+, to cohesively integrate all views of G into an MVAG Laplacian matrix, which readily enables classic graph algorithms to handle G with superior performance in clustering and embedding tasks. We begin by conducting a theoretical analysis to design an integrated objective that consists of two components, the eigengap and connectivity objectives, aiming to link the spectral properties of the aggregated MVAG Laplacian with the underlying community and connectivity properties of G. A constrained optimization problem is then formulated for the integration, which is computationally expensive to solve. Thus, we first develop the SGLA algorithm, which already achieves excellent performance compared with existing methods. To further enhance efficiency, we design SGLA+ to reduce the number of costly objective evaluations via sampling and approximation to quickly find an approximate optimum. Extensive experiments compare our methods against 12 baselines for clustering and 8 baselines for embedding on 8 multi-view attributed graphs, validating the superior performance of SGLA and SGLA+ in terms of result quality and efficiency. Compared with the most effective baselines, our methods are significantly faster, often by up to orders of magnitude.

cs.SI↗

arXiv2025

Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization

Generating images from rhetorical languages remains a critical challenge for text-to-image models. Even state-of-the-art (SOTA) multimodal large language models (MLLM) fail to generate images based on the hidden meaning inherent in rhetorical language--despite such content being readily mappable to visual representations by humans. A key limitation is that current models emphasize object-level word embedding alignment, causing metaphorical expressions to steer image generation towards their literal visuals and overlook the intended semantic meaning. To address this, we propose Rhet2Pix, a framework that formulates rhetorical text-to-image generation as a multi-step policy optimization problem, incorporating a two-layer MDP diffusion module. In the outer layer, Rhet2Pix converts the input prompt into incrementally elaborated sub-sentences and executes corresponding image-generation actions, constructing semantically richer visuals. In the inner layer, Rhet2Pix mitigates reward sparsity during image generation by discounting the final reward and optimizing every adjacent action pair along the diffusion denoising trajectory. Extensive experiments demonstrate the effectiveness of Rhet2Pix in rhetorical text-to-image generation. Our model outperforms SOTA MLLMs such as GPT-4o, Grok-3 and leading academic baselines across both qualitative and quantitative evaluations. The code and dataset used in this work are publicly available.

cs.CV↗

arXiv2025

A Survey on False Information Detection: From A Perspective of Propagation on Social Networks

The proliferation of false information in the digital age has become a pressing concern, necessitating the development of effective and robust detection methods. This paper offers a comprehensive review of existing false information detection techniques, approached from a novel perspective that emphasizes the propagation characteristics of misinformation. We introduce a new taxonomy that categorizes these methods into homogeneous and heterogeneous propagation-based approaches, providing a deeper understanding of the varying scopes and complexities involved in information dissemination. For each category, we present a formal problem formulation, review commonly used datasets, and summarize state-of-the-art methods. Additionally, we identify several promising directions for future research, including the creation of a unified benchmark suite, exploration of diverse information modalities, and development of innovative rumor debunking tasks. By systematically organizing the vast array of current techniques, this work offers a clear overview of the research landscape, aiding researchers and practitioners in navigating this complex field and inspiring further advancements.

cs.SI↗

arXiv2025

Rumor Detection on Social Media with Reinforcement Learning-based Key Propagation Graph Generator

The spread of rumors on social media, particularly during significant events like the US elections and the COVID-19 pandemic, poses a serious threat to social stability and public health. Current rumor detection methods primarily rely on propagation graphs to improve the model performance. However, the effectiveness of these methods is often compromised by noisy and irrelevant structures in the propagation process. To tackle this issue, techniques such as weight adjustment and data augmentation have been proposed. However, they depend heavily on rich original propagation structures, limiting their effectiveness in handling rumors that lack sufficient propagation information, especially in the early stages of dissemination. In this work, we introduce the Key Propagation Graph Generator (KPG), a novel reinforcement learning-based framework, that generates contextually coherent and informative propagation patterns for events with insufficient topology information and identifies significant substructures in events with redundant and noisy propagation structures. KPG comprises two key components: the Candidate Response Generator (CRG) and the Ending Node Selector (ENS). CRG learns latent variable distributions from refined propagation patterns to eliminate noise and generate new candidates for ENS, while ENS identifies the most influential substructures in propagation graphs and provides training data for CRG. Furthermore, we develop an end-to-end framework that utilizes rewards derived from a pre-trained graph neural network to guide the training process. The resulting key propagation graphs are then employed in downstream rumor detection tasks. Extensive experiments conducted on four datasets demonstrate that KPG outperforms current state-of-the-art methods.

cs.SI↗

arXiv2025

Finding Near-Optimal Maximum Set of Disjoint $k$-Cliques in Real-World Social Networks

A $k$-clique is a dense graph, consisting of $k$ fully-connected nodes, that finds numerous applications, such as community detection and network analysis. In this paper, we study a new problem, that finds a maximum set of disjoint $k$-cliques in a given large real-world graph with a user-defined fixed number $k$, which can contribute to a good performance of teaming collaborative events in online games. However, this problem is NP-hard when $k \geq 3$, making it difficult to solve. To address that, we propose an efficient lightweight method that avoids significant overheads and achieves a $k$-approximation to the optimal, which is equipped with several optimization techniques, including the ordering method, degree estimation in the clique graph, and a lightweight implementation. Besides, to handle dynamic graphs that are widely seen in real-world social networks, we devise an efficient indexing method with careful swapping operations, leading to the efficient maintenance of a near-optimal result with frequent updates in the graph. In various experiments on several large graphs, our proposed approaches significantly outperform the competitors by up to 2 orders of magnitude in running time and 13.3\% in the number of computed disjoint $k$-cliques, which demonstrates the superiority of the proposed approaches in terms of efficiency and effectiveness.

cs.SI↗

arXiv2025

In-medium $ΛN$ interactions with leading order covariant chiral hyperon/nucleon-nucleon forces

In-medium $ΛN$ interactions are crucial in hypernuclei and neutron star physics. In this work, we study the in-medium $ΛN$ interaction within the relativistic Brueckner-Hartree-Fock (RBHF) framework, employing the leading-order covariant chiral hyperon/nucleon-nucleon forces for the first time. We demonstrate that a consistent description of both the experimental cross-section data and the `empirical value' of the $Λ$ single-particle potential can be achieved. This contrasts with the majority of studies in the non-relativistic framework, where higher-order two-body chiral forces are typically required. This study offers a new perspective on the in-medium $ΛN$ interactions, urgently needed in relativistic \textit{ab initio} hypernuclear physics studies.

nucl-th↗

arXiv2025

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models

The rapid evolution of Large Vision-Language Models (LVLMs) has highlighted the necessity for comprehensive evaluation frameworks that assess these models across diverse dimensions. While existing benchmarks focus on specific aspects such as perceptual abilities, cognitive capabilities, and safety against adversarial attacks, they often lack the breadth and depth required to provide a holistic understanding of LVLMs' strengths and limitations. To address this gap, we introduce REVAL, a comprehensive benchmark designed to evaluate the \textbf{RE}liability and \textbf{VAL}ue of LVLMs. REVAL encompasses over 144K image-text Visual Question Answering (VQA) samples, structured into two primary sections: Reliability, which assesses truthfulness (\eg, perceptual accuracy and hallucination tendencies) and robustness (\eg, resilience to adversarial attacks, typographic attacks, and image corruption), and Values, which evaluates ethical concerns (\eg, bias and moral understanding), safety issues (\eg, toxicity and jailbreak vulnerabilities), and privacy problems (\eg, privacy awareness and privacy leakage). We evaluate 26 models, including mainstream open-source LVLMs and prominent closed-source models like GPT-4o and Gemini-1.5-Pro. Our findings reveal that while current LVLMs excel in perceptual tasks and toxicity avoidance, they exhibit significant vulnerabilities in adversarial scenarios, privacy preservation, and ethical reasoning. These insights underscore critical areas for future improvements, guiding the development of more secure, reliable, and ethically aligned LVLMs. REVAL provides a robust framework for researchers to systematically assess and compare LVLMs, fostering advancements in the field.

cs.CV↗

arXiv2025

Optimal Approximate Matrix Multiplication over Sliding Window

Matrix multiplication is a core operation in numerous applications, yet its exact computation becomes prohibitively expensive as data scales, especially in streaming environments where timeliness is critical. In many real-world scenarios, data arrives continuously, making it essential to focus on recent information via sliding windows. While existing approaches offer approximate solutions, they often suffer from suboptimal space complexities when extended to the sliding-window setting. In this work, we introduce SO-COD, a novel algorithm for approximate matrix multiplication (AMM) in the sliding-window streaming setting, where only the most recent data is retained for computation. Inspired by frequency estimation over sliding windows, our method tracks significant contributions, referred to as snapshots, from incoming data and efficiently updates them as the window advances. Given matrices $\boldsymbol{X} \in \mathbb{R}^{d_x \times n}$ and $\boldsymbol{Y} \in \mathbb{R}^{d_y \times n}$ for computing $\boldsymbol{X} \boldsymbol{Y}^T$, we analyze two data settings. In the \emph{normalized} setting, where each column of the input matrices has a unit $L_2$ norm, SO-COD achieves an optimal space complexity of $ O\left(\frac{d_x+d_y}ε\right) $. In the \emph{unnormalized} setting, where the square of column norms vary within a bounded range $[1, R]$, we show that the space requirement is $ O\left(\frac{d_x+d_y}ε\log R\right) $, which matches the theoretical lower bound for an $ε$-approximation guarantee. Extensive experiments on synthetic and real-world datasets demonstrate that SO-COD effectively balances space cost and approximation error, making it a promising solution for large-scale, dynamic streaming matrix multiplication.

cs.DS↗

arXiv2025

Towards More Accurate Full-Atom Antibody Co-Design

Antibody co-design represents a critical frontier in drug development, where accurate prediction of both 1D sequence and 3D structure of complementarity-determining regions (CDRs) is essential for targeting specific epitopes. Despite recent advances in equivariant graph neural networks for antibody design, current approaches often fall short in capturing the intricate interactions that govern antibody-antigen recognition and binding specificity. In this work, we present Igformer, a novel end-to-end framework that addresses these limitations through innovative modeling of antibody-antigen binding interfaces. Our approach refines the inter-graph representation by integrating personalized propagation with global attention mechanisms, enabling comprehensive capture of the intricate interplay between local chemical interactions and global conformational dependencies that characterize effective antibody-antigen binding. Through extensive validation on epitope-binding CDR design and structure prediction tasks, Igformer demonstrates significant improvements over existing methods, suggesting that explicit modeling of multi-scale residue interactions can substantially advance computational antibody design for therapeutic applications.

q-bio.BM↗

arXiv2025

Fast and Accurate Antibody Sequence Design via Structure Retrieval

Recent advancements in protein design have leveraged diffusion models to generate structural scaffolds, followed by a process known as protein inverse folding, which involves sequence inference on these scaffolds. However, these methodologies face significant challenges when applied to hyper-variable structures such as antibody Complementarity-Determining Regions (CDRs), where sequence inference frequently results in non-functional sequences due to hallucinations. Distinguished from prevailing protein inverse folding approaches, this paper introduces Igseek, a novel structure-retrieval framework that infers CDR sequences by retrieving similar structures from a natural antibody database. Specifically, Igseek employs a simple yet effective multi-channel equivariant graph neural network to generate high-quality geometric representations of CDR backbone structures. Subsequently, it aligns sequences of structurally similar CDRs and utilizes structurally conserved sequence motifs to enhance inference accuracy. Our experiments demonstrate that Igseek not only proves to be highly efficient in structural retrieval but also outperforms state-of-the-art approaches in sequence recovery for both antibodies and T-Cell Receptors, offering a new retrieval-based perspective for therapeutic protein design.

q-bio.BM↗

arXiv2025

SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels

Node Anomaly Detection (NAD) has gained significant attention in the deep learning community due to its diverse applications in real-world scenarios. Existing NAD methods primarily embed graphs within a single Euclidean space, while overlooking the potential of non-Euclidean spaces. Besides, to address the prevalent issue of limited supervision in real NAD tasks, previous methods tend to leverage synthetic data to collect auxiliary information, which is not an effective solution as shown in our experiments. To overcome these challenges, we introduce a novel SpaceGNN model designed for NAD tasks with extremely limited labels. Specifically, we provide deeper insights into a task-relevant framework by empirically analyzing the benefits of different spaces for node representations, based on which, we design a Learnable Space Projection function that effectively encodes nodes into suitable spaces. Besides, we introduce the concept of weighted homogeneity, which we empirically and theoretically validate as an effective coefficient during information propagation. This concept inspires the design of the Distance Aware Propagation module. Furthermore, we propose the Multiple Space Ensemble module, which extracts comprehensive information for NAD under conditions of extremely limited supervision. Our findings indicate that this module is more beneficial than data augmentation techniques for NAD. Extensive experiments conducted on 9 real datasets confirm the superiority of SpaceGNN, which outperforms the best rival by an average of 8.55% in AUC and 4.31% in F1 scores. Our code is available at https://github.com/xydong127/SpaceGNN.

cs.LG↗

arXiv2025

Speed of sound bounds and first-order phase transitions in compact stars

In the present study, we employ three distinct, physically motivated speed of sound bounds to construct hybrid models, where the high-density phase is described by the maximally stiff equation of state. In particular, we consider the bounds related to special relativity, relativistic kinetic theory and conformality. The low-density hadronic phase is described by a state-of-the-art microscopic relativistic Brueckner-Hartree-Fock theory. This work aims to access the effect of the different speed of sound constraints on the relevant parameter space of the key parameters of first-order phase transitions by utilizing recent astronomical data. This involves a systematic analysis that also includes two distinct schemes for the construction of hybrid models (abrupt and smooth). Finally, a relevant discussion is conducted on the possible occurrence of a thermodynamic inconsistency that is related to the stability of the high-density phase over hadronic matter at large densities.

astro-ph.HE↗

arXiv2025

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models. While such sanitized conditions simplify evaluation, they fail to capture the unpredictable, noisy complexities of real-world environments. Dynamic motion, sensor imperfections, and synchronization perturbations lead to sharp performance declines when these models are deployed in practice, revealing an urgent need for frameworks that embrace and excel under real-world noise. To bridge this gap, we tackle three core challenges: scalable data generation, comprehensive benchmarking, and model robustness enhancement. First, we introduce a scalable noisy data synthesis pipeline that generates diverse datasets simulating complex motion, sensor imperfections, and synchronization errors. Second, we leverage this pipeline to create Robust-Ego3D, a benchmark rigorously designed to expose noise-induced performance degradation, highlighting the limitations of current learning-based methods in ego-motion accuracy and 3D reconstruction quality. Third, we propose Correspondence-guided Gaussian Splatting (CorrGS), a novel test-time adaptation method that progressively refines an internal clean 3D representation by aligning noisy observations with rendered RGB-D frames from clean 3D map, enhancing geometric alignment and appearance restoration through visual correspondence. Extensive experiments on synthetic and real-world data demonstrate that CorrGS consistently outperforms prior state-of-the-art methods, particularly in scenarios involving rapid motion and dynamic illumination.

cs.CV↗

arXiv2024

DIPS: Optimal Dynamic Index for Poisson $\boldsymbolπ$ps Sampling

This paper addresses the Poisson $π$ps sampling problem, a topic of significant academic interest in various domains and with practical data mining applications, such as influence maximization. The problem includes a set $\mathcal{S}$ of $n$ elements, where each element $v$ is assigned a weight $w(v)$ reflecting its importance. The goal is to generate a random subset $X$ of $\mathcal{S}$, where each element $v \in \mathcal{S}$ is included in $X$ independently with probability $\frac{c\cdot w(v)}{\sum_{v \in \mathcal{S}} w(v)}$, where $0<c\leq 1$ is a constant. The subsets must be independent across different queries. While the Poisson $π$ps sampling problem can be reduced to the well-studied subset sampling problem, updates in Poisson $π$ps sampling, such as adding a new element or removing an element, would cause the probabilities of all $n$ elements to change in the corresponding subset sampling problem, making this approach impractical for dynamic scenarios. To address this, we propose a dynamic index specifically tailored for the Poisson $π$ps sampling problem, supporting optimal expected $\mathcal{O}(1)$ query time and $\mathcal{O}(1)$ index update time, with an optimal $\mathcal{O}(n)$ space cost. Our solution involves recursively partitioning the set by weights and ultimately using table lookup. The core of our solution lies in addressing the challenges posed by weight explosion and correlations between elements. Empirical evaluations demonstrate that our approach achieves significant speedups in update time while maintaining consistently competitive query time compared to the subset-sampling-based methods.

cs.DB↗

arXiv2024

Dynamic Structural Clustering Unleashed: Flexible Similarities, Versatile Updates and for All Parameters

We study structural clustering on graphs in dynamic scenarios, where the graphs can be updated by arbitrary insertions or deletions of edges/vertices. The goal is to efficiently compute structural clustering results for any clustering parameters $ε$ and $μ$ given on the fly, for arbitrary graph update patterns, and for all typical similarity measurements. Specifically, we adopt the idea of update affordability and propose an a-lot-simpler yet more efficient (both theoretically and practically) algorithm (than state of the art), named VD-STAR to handle graph updates. First, with a theoretical clustering result quality guarantee, VD-STAR can output high-quality clustering results with up to 99.9% accuracy. Second, our VD-STAR is easy to implement as it just needs to maintain certain sorted linked lists and hash tables, and hence, effectively enhances its deployment in practice. Third and most importantly, by careful analysis, VD-STAR improves the per-update time bound of the state-of-the-art from $O(\log^2 n)$ expected with certain update pattern assumption to $O(\log n)$ amortized in expectation without any update pattern assumption. We further design two variants of VD-STAR to enhance its empirical performance. Experimental results show that our algorithms consistently outperform the state-of-the-art competitors by up to 9,315 times in update time across nine real datasets.

cs.DS↗