arXiv subjects

Chuang Liu

Publications and source records attributed to Chuang Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Structural-Aware Key Node Identification in Hypergraphs via Representation Learning and Fine-Tuning

Evaluating node importance is a critical aspect of analyzing complex systems, with broad applications in digital marketing, rumor suppression, and disease control. However, existing methods typically rely on conventional network structures and fail to capture the polyadic interactions intrinsic to many real-world systems. To address this limitation, we study key node identification in hypergraphs, where higher-order interactions are naturally modeled as hyperedges. We propose a novel framework, AHGA, which integrates an Autoencoder for extracting higher-order structural features, a HyperGraph neural network-based pre-training module (HGNN), and an Active learning-based fine-tuning process. This fine-tuning step plays a vital role in mitigating the gap between synthetic and real-world data, thereby enhancing the model's robustness and generalization across diverse hypergraph topologies. Extensive experiments on eight empirical hypergraphs show that AHGA outperforms classical centrality-based baselines by approximately 37.4%. Furthermore, the nodes identified by AHGA exhibit both high influence and strong structural disruption capability, demonstrating their superiority in detecting multifunctional nodes.

cs.SI↗

arXiv2025

Source Detection in Hypergraph Epidemic Dynamics using a Higher-Order Dynamic Message Passing Algorithm

Source detection is crucial for capturing the dynamics of real-world infectious diseases and informing effective containment strategies. Most existing approaches to source detection focus on conventional pairwise networks, whereas recent efforts on both mathematical modeling and analysis of contact data suggest that higher-order (e.g., group) interactions among individuals may both account for a large fraction of infection events and change our understanding of how epidemic spreading proceeds in empirical populations. In the present study, we propose a message-passing algorithm, called the HDMPN, for source detection for a stochastic susceptible-infectious dynamics on hypergraphs. By modulating the likelihood maximization method by the fraction of infectious neighbors, HDMPN aims to capture the influence of higher-order structures and do better than the conventional likelihood maximization. We numerically show that, in most cases, HDMPN outperforms benchmarks including the likelihood maximization method without modification.

physics.soc-ph↗

arXiv2025

Indeterminate Probability Theory

Complex continuous or mixed joint distributions (e.g., P(Y | z_1, z_2, ..., z_N)) generally lack closed-form solutions, often necessitating approximations such as MCMC. This paper proposes Indeterminate Probability Theory (IPT), which makes the following contributions: (1) An observer-centered framework in which experimental outcomes are represented as distributions combining ground truth with observation error; (2) The introduction of three independence candidate axioms that enable a two-phase probabilistic inference framework; (3) The derivation of closed-form solutions for arbitrary complex joint distributions under this framework. Both the Indeterminate Probability Neural Network (IPNN) model and the non-neural multivariate time series forecasting application demonstrate IPT's effectiveness in modeling high-dimensional distributions, with successful validation up to 1000 dimensions. Importantly, IPT is consistent with classical probability theory and subsumes the frequentist equation in the limit of vanishing observation error.

cs.LG↗

arXiv2025

BPO: Revisiting Preference Modeling in Direct Preference Optimization

Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through pairwise ranking losses, it often neglects absolute reward magnitudes. This oversight can decrease the likelihood of chosen responses and increase the risk of generating out-of-distribution responses, leading to poor performance. We term this issue Degraded Chosen Responses (DCR).To address this issue, we propose Balanced Preference Optimization (BPO), a novel framework that dynamically balances the optimization of chosen and rejected responses through two key components: balanced reward margin and gap adaptor. Unlike previous methods, BPO can fundamentally resolve DPO's DCR issue, without introducing additional constraints to the loss function. Experimental results on multiple mathematical reasoning tasks show that BPO significantly outperforms DPO, improving accuracy by +10.1% with Llama-3.1-8B-Instruct (18.8% to 28.9%) and +11.7% with Qwen2.5-Math-7B (35.0% to 46.7%). It also surpasses DPO variants by +3.6% over IPO (43.1%), +5.0% over SLiC (41.7%), and +3.1% over Cal-DPO (43.6%) on the same model. Remarkably, our algorithm requires only a single line of code modification, making it simple to implement and fully compatible with existing DPO-based frameworks.

cs.CL↗

arXiv2025

FreePRM: Training Process Reward Models Without Ground Truth Process Labels

Recent advancements in Large Language Models (LLMs) have demonstrated that Process Reward Models (PRMs) play a crucial role in enhancing model performance. However, training PRMs typically requires step-level labels, either manually annotated or automatically generated, which can be costly and difficult to obtain at scale. To address this challenge, we introduce FreePRM, a weakly supervised framework for training PRMs without access to ground-truth step-level labels. FreePRM first generates pseudo step-level labels based on the correctness of final outcome, and then employs Buffer Probability to eliminate impact of noise inherent in pseudo labeling. Experimental results show that FreePRM achieves an average F1 score of 53.0% on ProcessBench, outperforming fully supervised PRM trained on Math-Shepherd by +24.1%. Compared to other open-source PRMs, FreePRM outperforms upon RLHFlow-PRM-Mistral-8B (28.4%) by +24.6%, EurusPRM (31.3%) by +21.7%, and Skywork-PRM-7B (42.1%) by +10.9%. This work introduces a new paradigm in PRM training, significantly reducing reliance on costly step-level annotations while maintaining strong performance.

cs.CL↗

arXiv2025

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis

Video generative models can be regarded as world simulators due to their ability to capture dynamic, continuous changes inherent in real-world environments. These models integrate high-dimensional information across visual, temporal, spatial, and causal dimensions, enabling predictions of subjects in various status. A natural and valuable research direction is to explore whether a fully trained video generative model in high-dimensional space can effectively support lower-dimensional tasks such as controllable image generation. In this work, we propose a paradigm for video-to-image knowledge compression and task adaptation, termed \textit{Dimension-Reduction Attack} (\texttt{DRA-Ctrl}), which utilizes the strengths of video models, including long-range context modeling and flatten full-attention, to perform various generation tasks. Specially, to address the challenging gap between continuous video frames and discrete image generation, we introduce a mixup-based transition strategy that ensures smooth adaptation. Moreover, we redesign the attention structure with a tailored masking mechanism to better align text prompts with image-level control. Experiments across diverse image generation tasks, such as subject-driven and spatially conditioned generation, show that repurposed video models outperform those trained directly on images. These results highlight the untapped potential of large-scale video generators for broader visual applications. \texttt{DRA-Ctrl} provides new insights into reusing resource-intensive video models and lays foundation for future unified generative models across visual modalities. The project page is https://dra-ctrl-2025.github.io/DRA-Ctrl/.

cs.CV↗

arXiv2025

Modeling Coupled Epidemic-Information Dynamics via Reaction-Diffusion Processes on Multiplex Networks with Media and Mobility Effects

While most existing epidemic models focus on the influence of isolated factors, infectious disease transmission is inherently shaped by the complex interplay of multiple interacting elements. To better capture real-world dynamics, it is essential to develop epidemic models that incorporate diverse, realistic factors. In this study, we propose a coupled disease-information spreading model on multiplex networks that simultaneously accounts for three critical dimensions: media influence, higher-order interactions, and population mobility. This integrated framework enables a systematic analysis of synergistic spreading mechanisms under practical constraints and facilitates the exploration of effective epidemic containment strategies. We employ a microscopic Markov chain approach (MMCA) to derive the coupled dynamical equations and identify epidemic thresholds, which are then validated through extensive Monte Carlo (MC) simulations. Our results show that both mass media dissemination and higher-order network structures contribute to suppressing disease transmission by enhancing public awareness. However, the containment effect of higher-order interactions weakens as the order of simplices increases. We also explore the influence of subpopulation characteristics, revealing that increasing inter-subpopulation connectivity in a connected metapopulation network leads to lower disease prevalence. Furthermore, guiding individuals to migrate toward less accessible or more isolated subpopulations is shown to effectively mitigate epidemic spread. These findings offer valuable insights for designing targeted and adaptive intervention strategies in complex epidemic settings.

physics.soc-ph↗

arXiv2025

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

Explainability is a critical factor influencing the wide deployment of deep vision models (DVMs). Concept-based post-hoc explanation methods can provide both global and local insights into model decisions. However, current methods in this field face challenges in that they are inflexible to automatically construct accurate and sufficient linguistic explanations for global concepts and local circuits. Particularly, the intrinsic polysemanticity in semantic Visual Concepts (VCs) impedes the interpretability of concepts and DVMs, which is underestimated severely. In this paper, we propose a Chain-of-Explanation (CoE) approach to address these issues. Specifically, CoE automates the decoding and description of VCs to construct global concept explanation datasets. Further, to alleviate the effect of polysemanticity on model explainability, we design a concept polysemanticity disentanglement and filtering mechanism to distinguish the most contextually relevant concept atoms. Besides, a Concept Polysemanticity Entropy (CPE), as a measure of model interpretability, is formulated to quantify the degree of concept uncertainty. The modeling of deterministic concepts is upgraded to uncertain concept atom distributions. Finally, CoE automatically enables linguistic local explanations of the decision-making process of DVMs by tracing the concept circuit. GPT-4o and human-based experiments demonstrate the effectiveness of CPE and the superiority of CoE, achieving an average absolute improvement of 36% in terms of explainability scores.

cs.CV↗

arXiv2025

Numerical Study On Temperature Variations Of Superheated Steam Flowing Through A Regulation Valve

Superheated steam is widely employed in various energy systems, particularly in power plants, chemical industries, and other applications where high-temperature and high-pressure steam is essential for efficient energy conversion and process control. In these systems, regulation valves are crucial components that control the flow of steam, adjusting its pressure and temperature to ensure safe and efficient operation. Accurate understanding and prediction of temperature variations within regulation valves are essential for optimizing their performance and improving the overall system efficiency. This study investigates the temperature variations of superheated steam flowing through a regulation valve using computational fluid dynamics (CFD) simulations combined with Proper Orthogonal Decomposition (POD) techniques. The analysis begins with an examination of the internal flow field parameters, including temperature and pressure, to understand the overall fluid dynamics within the valve. POD is applied to reduce the dimensionality of the CFD results. Singular Value Decomposition (SVD) is employed to extract the dominant modes that capture the key flow structures responsible for heat transfer and temperature fluctuations. The POD analysis reveals that the most influential modes are associated with regions of high turbulence intensity and significant temperature gradients, which are critical to the thermal performance of the steam flow through the regulation valve. The application of POD to 3D CFD results represents a novel approach, particularly for complex fluid flow models such as steam flow through regulation valves. The insights gained from this study have practical implications for the design and optimization of temperature and pressure regulation valves in energy systems, providing a theoretical foundation for enhancing the efficiency and reliability of these systems.

physics.flu-dyn↗

arXiv2024

Large Language Model Safety: A Holistic Survey

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies. This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks. In addition to the comprehensive review of the mitigation methodologies and evaluation resources on these four aspects, we further explore four topics related to LLM safety: the safety implications of LLM agents, the role of interpretability in enhancing LLM safety, the technology roadmaps proposed and abided by a list of AI companies and institutes for LLM safety, and AI governance aimed at LLM safety with discussions on international cooperation, policy proposals, and prospective regulatory directions. Our findings underscore the necessity for a proactive, multifaceted approach to LLM safety, emphasizing the integration of technical solutions, ethical considerations, and robust governance frameworks. This survey is intended to serve as a foundational resource for academy researchers, industry practitioners, and policymakers, offering insights into the challenges and opportunities associated with the safe integration of LLMs into society. Ultimately, it seeks to contribute to the safe and beneficial development of LLMs, aligning with the overarching goal of harnessing AI for societal advancement and well-being. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLM-Safety-Papers.

cs.AI↗

arXiv2024

DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts

Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. In real-world scenarios, graph data within the same dataset can vary significantly in scale. This variability leads to depth-sensitivity, where the optimal depth of GNN layers depends on the scale of the graph data. Empirically, fewer layers are sufficient for message passing in smaller graphs, while larger graphs typically require deeper networks to capture long-range dependencies and global features. However, existing methods generally use a fixed number of GNN layers to generate representations for all graphs, overlooking the depth-sensitivity issue in graph structure data. To address this challenge, we propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN backbone: \textbf{1)} DA-MoE employs different GNN layers, each considered an expert with its own parameters. Such a design allows the model to flexibly aggregate information at different scales, effectively addressing the depth-sensitivity issue in graph data. \textbf{2)} DA-MoE utilizes GNN to capture the structural information instead of the linear projections in the gating network. Thus, the gating network enables the model to capture complex patterns and dependencies within the data. By leveraging these improvements, each expert in DA-MoE specifically learns distinct graph patterns at different scales. Furthermore, comprehensive experiments on the TU dataset and open graph benchmark (OGB) have shown that DA-MoE consistently surpasses existing baselines on various tasks, including graph, node, and link-level analyses. The code are available at \url{https://github.com/Celin-Yao/DA-MoE}.

cs.LG↗

arXiv2024

BCIM: Budget and capacity constrained influence maximization in multilayer networks

Influence maximization (IM) seeks to identify a seed set that maximizes influence within a network, with applications in areas such as viral marketing, disease control, and political campaigns. The budgeted influence maximization (BIM) problem extends IM by incorporating cost constraints for different nodes. However, the current BIM problem, limited by budget alone, often results in the selection of numerous low-cost nodes, which may not be applicable to real-world scenarios. Moreover, considering that users can transmit information across multiple social platforms, solving the BIM problem across these platforms could lead to more optimized resource utilization. To address these challenges, we propose the Budget and Capacity Constrained Influence Maximization (BCIM) problem within multilayer networks and introduce a Multilayer Multi-population Genetic Algorithm (MMGA) to solve it. The MMGA employs modules, such as initialization, repair, and parallel evolution, designed not only to meet budget and capacity constraints but also to significantly enhance algorithmic efficiency. Extensive experiments on both synthetic and empirical multilayer networks demonstrate that MMGA improves spreading performance by at least 10% under the two constraints compared to baselines extended from classical IM problems. The BCIM framework introduces a novel direction in influence maximization, providing an effective and efficient solution to the problem.

cs.SI↗

arXiv2024

ESND: An Embedding-based Framework for Signed Network Dismantling

Network dismantling aims to maximize the disintegration of a network by removing a specific set of nodes or edges and is applied to various tasks in diverse domains, such as cracking down on crime organizations, delaying the propagation of rumors, and blocking the transmission of viruses. Most of the current network dismantling methods are tailored for unsigned networks, which only consider the connection between nodes without evaluating the nature of the relationships, such as friendship/hostility, enhancing/repressing, and trust/distrust. We here propose an embedding-based algorithm, namely ESND, to solve the signed network dismantling problem. The algorithm generally iterates the following four steps, i.e., giant component detection, network embedding, node clustering, and removal node selection. To illustrate the efficacy and stability of ESND, we conduct extensive experiments on six signed network datasets as well as null models, and compare the performance of our method with baselines. Experimental results consistently show that the proposed ESND is superior to the baselines and displays stable performance with the change in the network structure. Additionally, we examine the impact of sign proportions on network robustness via ESND, observing that networks with a high ratio of negative edges are generally easier to dismantle than networks with high positive edges.

physics.soc-ph↗

arXiv2024

Dual-perspective Cross Contrastive Learning in Graph Transformers

Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective) augmentation to generate positive samples, restraining the diversity of positive samples. In addition, these positive samples may be unreliable due to uncontrollable augmentation strategies that potentially alter the semantic information. To address these challenges, this paper proposed a innovative framework termed dual-perspective cross graph contrastive learning (DC-GCL), which incorporates three modifications designed to enhance positive sample diversity and reliability: 1) We propose dual-perspective augmentation strategy that provide the model with more diverse training data, enabling the model effective learning of feature consistency across different views. 2) From the data perspective, we slightly perturb the original graphs using controllable data augmentation, effectively preserving their semantic information. 3) From the model perspective, we enhance the encoder by utilizing more powerful graph transformers instead of graph neural networks. Based on the model's architecture, we propose three pruning-based strategies to slightly perturb the encoder, providing more reliable positive samples. These modifications collectively form the DC-GCL's foundation and provide more diverse and reliable training inputs, offering significant improvements over traditional GCL methods. Extensive experiments on various benchmarks demonstrate that DC-GCL consistently outperforms different baselines on various datasets and tasks.

cs.LG↗

arXiv2024

Gradformer: Graph Transformer with Exponential Decay

Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for the graph tasks. Although some methods utilize positional encoding and attention bias to model inductive biases, their effectiveness is still suboptimal analytically. Therefore, this paper presents Gradformer, a method innovatively integrating GT with the intrinsic inductive bias by applying an exponential decay mask to the attention matrix. Specifically, the values in the decay mask matrix diminish exponentially, correlating with the decreasing node proximities within the graph structure. This design enables Gradformer to retain its ability to capture information from distant nodes while focusing on the graph's local details. Furthermore, Gradformer introduces a learnable constraint into the decay mask, allowing different attention heads to learn distinct decay masks. Such an design diversifies the attention heads, enabling a more effective assimilation of diverse structural information within the graph. Extensive experiments on various benchmarks demonstrate that Gradformer consistently outperforms the Graph Neural Network and GT baseline models in various graph classification and regression tasks. Additionally, Gradformer has proven to be an effective method for training deep GT models, maintaining or even enhancing accuracy compared to shallow models as the network deepens, in contrast to the significant accuracy drop observed in other GT models.Codes are available at \url{https://github.com/LiuChuang0059/Gradformer}.

cs.LG↗

arXiv2024

Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders

Graph masked autoencoders (GMAE) have emerged as a significant advancement in self-supervised pre-training for graph-structured data. Previous GMAE models primarily utilize a straightforward random masking strategy for nodes or edges during training. However, this strategy fails to consider the varying significance of different nodes within the graph structure. In this paper, we investigate the potential of leveraging the graph's structural composition as a fundamental and unique prior in the masked pre-training process. To this end, we introduce a novel structure-guided masking strategy (i.e., StructMAE), designed to refine the existing GMAE models. StructMAE involves two steps: 1) Structure-based Scoring: Each node is evaluated and assigned a score reflecting its structural significance. Two distinct types of scoring manners are proposed: predefined and learnable scoring. 2) Structure-guided Masking: With the obtained assessment scores, we develop an easy-to-hard masking strategy that gradually increases the structural awareness of the self-supervised reconstruction task. Specifically, the strategy begins with random masking and progresses to masking structure-informative nodes based on the assessment scores. This design gradually and effectively guides the model in learning graph structural information. Furthermore, extensive experiments consistently demonstrate that our StructMAE method outperforms existing state-of-the-art GMAE models in both unsupervised and transfer learning tasks. Codes are available at https://github.com/LiuChuang0059/StructMAE.

cs.LG↗

arXiv2024

Locating influential nodes in hypergraphs via fuzzy collective influence

Complex contagion phenomena, such as the spread of information or contagious diseases, often occur among the population due to higher-order interactions between individuals. Individuals who can be represented by nodes in a network may play different roles in the spreading process, and thus finding the most influential nodes in a network has become a crucial topic in network science for applications such as viral marketing, rumor suppression, and disease control. To solve the problem of identifying nodes that have high influence in a complex system, we propose a higher-order distance-based fuzzy centrality methods (HDF and EHDF) that are customized for a hypergraph which can characterize higher-order interactions between nodes via hyperedges. The methods we proposed assume that the influence of a node is reliant on the neighboring nodes with a certain higher-order distance. We compare the proposed methods with the baseline centrality methods to verify their effectiveness. Experimental results on six empirical hypergraphs show that the proposed methods could better identify influential nodes, especially showing plausible performance in finding the top influential nodes. Our proposed theoretical framework for identifying influential nodes could provide insights into how higher-order topological structure can be used for tasks such as vital node identification, influence maximization, and network dismantling.

physics.soc-ph↗

arXiv2024

LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models

Chinese Large Language Models (LLMs) have recently demonstrated impressive capabilities across various NLP benchmarks and real-world applications. However, the existing benchmarks for comprehensively evaluating these LLMs are still insufficient, particularly in terms of measuring knowledge that LLMs capture. Current datasets collect questions from Chinese examinations across different subjects and educational levels to address this issue. Yet, these benchmarks primarily focus on objective questions such as multiple-choice questions, leading to a lack of diversity in question types. To tackle this problem, we propose LHMKE, a Large-scale, Holistic, and Multi-subject Knowledge Evaluation benchmark in this paper. LHMKE is designed to provide a comprehensive evaluation of the knowledge acquisition capabilities of Chinese LLMs. It encompasses 10,465 questions across 75 tasks covering 30 subjects, ranging from primary school to professional certification exams. Notably, LHMKE includes both objective and subjective questions, offering a more holistic evaluation of the knowledge level of LLMs. We have assessed 11 Chinese LLMs under the zero-shot setting, which aligns with real examinations, and compared their performance across different subjects. We also conduct an in-depth analysis to check whether GPT-4 can automatically score subjective predictions. Our findings suggest that LHMKE is a challenging and advanced testbed for Chinese LLMs.

cs.CL↗