Modern Large Language Model (LLM) training clusters increasingly mix heterogeneous GPUs, diverse intra-node fabrics, and inter-node interconnects, combined with varied parallelism strategies. Exploring this massive design space, further amplified by heterogeneity, through real deployments is prohibitively slow and costly. Existing simulators, which are primarily designed and tuned for homogeneous clusters, either trade fidelity for speed or require heavyweight workflows with non-negligible overhead. We propose HeteroSim, a high-fidelity simulation framework for heterogeneous LLM training systems. It introduces: (i) a LLM training workload compiler that captures realistic training graphs, microbatching schedules, and compute-communication overlap; (ii) a heterogeneity-aware computation planner using roofline-style scaling across GPU generations; (iii) a collective communication planner that reproduces NCCL-like behaviors with per-link models, message channelization, and configurable routing. Across a wide range of heterogeneity levels, experimental results show that HeteroSim achieves near-real simulation accuracy while keeping low overhead.
论文检索
输入标题、作者或关键词，从 3,112 篇学术成果中精准定位
Generative agents are rapidly advancing in sophistication, raising urgent questions about how they might coordinate when deployed in online ecosystems. This is particularly consequential in information operations (IOs), influence campaigns that aim to manipulate public opinion on social media. While traditional IOs have been orchestrated by human operators and relied on manually crafted tactics, agentic AI promises to make campaigns more automated, adaptive, and difficult to detect. This work presents the first systematic study of emergent coordination among generative agents in simulated IO campaigns. Using generative agent-based modeling, we instantiate IO and organic agents in a simulated environment and evaluate coordination across operational regimes, from simple goal alignment to team knowledge and collective decision-making. As operational regimes become more structured, IO networks become denser and more clustered, interactions more reciprocal and positive, narratives more homogeneous, amplification more synchronized, and hashtag adoption faster and more sustained. Remarkably, simply revealing to agents which other agents share their goals can produce coordination levels nearly equivalent to those achieved through explicit deliberation and collective voting. Overall, we show that generative agents, even without human guidance, can reproduce coordination strategies characteristic of real-world IOs, underscoring the societal risks posed by increasingly automated, self-organizing IOs.
As a fundamental technique with many real-world applications, including social network analysis, center-based clustering may inadvertently discriminate against certain populations based on factors such as age, gender, or socioeconomic status, particularly when nodes are associated with sensitive attributes. In this work, we study the problem of fair k-center clustering in the streaming setting, which seeks to select representative items from a large data stream while respecting group-representation fairness. Given an input dataset in Euclidean space partitioned into m disjoint groups, the fairness constraint requires that the number of centers selected from each group satisfies a given upper bound. Moreover, the problem aims to select a set of centers that minimizes the maximum distance from any point to its nearest center (the k-center objective) while satisfying the fairness constraint. We present a one-pass streaming algorithm with approximation ratio 4.46, improving the previous best ratio of (5+?) for this problem in general metrics. Notably, our result establishes that streaming fair k-center admits a strictly better approximation ratio in Euclidean space than in general metrics, in contrast to the standard k-center problem, whose best-known approximation ratio is 2 in both Euclidean and general metric spaces. Finally, we complement our theoretical results with an empirical evaluation on five real-world social network datasets and million-scale synthetic datasets, demonstrating significant improvements over state-of-the-art methods in clustering quality while maintaining comparable runtime efficiency.
Dynamic graph clustering aims to detect and track time-varying clusters in dynamic graphs, revealing how complex real-world systems evolve over time. However, existing methods are predominantly black-box models. They lack interpretability in their clustering decisions and fail to provide semantic explanations of why clusters form or how they evolve, severely limiting their use in safety-critical domains such as healthcare or transportation. To address these limitations, we propose an end-to-end interpretable framework that maps continuous graph embeddings into discrete semantic concepts through learnable prototypes. Specifically, we first decompose node representations into orthogonal role and clustering subspaces, so that nodes with similar roles (e.g., hubs, bridges) but different cluster affiliations can be properly distinguished. We then introduce five node role prototypes (Leader, Contributor, Wanderer, Connector, Newcomer) in the role subspace as semantic anchors, transforming continuous embeddings into discrete concepts to facilitate LLM understanding of node roles within communities. Finally, we design a hierarchical LLM reasoning mechanism to generate both clustering results and natural language explanations, while providing consistency feedback as weak supervision to refine node representations. Experimental results on four synthetic and six real-world benchmarks demonstrate the effectiveness, interpretability, and robustness of DyG-RoLLM. Code is available at https: //github.com/Clearloveyuan/DyG-RoLLM.
As social media and the World Wide Web become hubs for information dissemination, effectively organizing and understanding the vast amounts of dynamically evolving Web content is crucial. Knowledge graphs (KGs) provide a powerful framework for structuring this information. However, the rapid emergence of new hot topics, user relationships, and events in social media renders traditional static knowledge graph embedding (KGE) models rapidly outdated. Continual Knowledge Graph Embedding (CKGE) aims to address this issue, but existing methods commonly suffer from catastrophic forgetting, whereby older, but still valuable, information is lost when learning new knowledge (such as new memes or trending events). This means the model cannot effectively learn the evolution of the data. We propose a novel CKGE framework, BAKE. Unlike existing methods, BAKE formulates CKGE as a sequential Bayesian inference problem and utilizes the Bayesian posterior update principle as a natural continual learning strategy. This principle is insensitive to data order and provides theoretical guarantees to preserve prior knowledge as much as possible. Specifically, we treat each batch of new data as a Bayesian update to the model's prior. By maintaining the posterior distribution, the model effectively preserves earlier knowledge even as it evolves over multiple snapshots. Furthermore, to constrain the evolution of knowledge across snapshots, we introduce a continual clustering method that maintains the compact cluster structure of entity embeddings through a regularization term, ensuring semantic consistency while allowing controlled adaptation to new knowledge. We conduct extensive experiments on multiple CKGE benchmarks, which demonstrate that BAKE achieves the top performance in the vast majority of cases compared to existing approaches.
The evaluation of Kleene Closure Property Path Queries (KPPQs) over RDF graphs presents a fundamental trade-off. Under the intuitive simple path semantics, which forbids node repetition, the problem is NP-complete. This forces practical systems to adopt existential path semantics, which admits tractable evaluation but produces result sets bloated with redundant and often semantically meaningless paths due to unnecessary detours through cycles. This paper introduces a novel indexing framework that effectively navigates this trade-off. Our key insight is that while enumerating all simple paths is intractable, a carefully selected, compact set of representative simple paths is sufficient to correctly and completely answer connectivity queries in practice. We propose the Node Clustered Index (NCI), which pre-materializes such paths—including the longest acyclic chains and fundamental cycles —transforming online query processing from a costly graph traversal into an efficient index lookup and expansion operation. Crucially, our method guarantees that every result conforms to simple path semantics. Extensive experiments demonstrate that our approach achieves near-perfect recall, outperforming state-of-the-art systems by up to an order of magnitude. This work establishes that for NP-complete path problems, seeking polynomial-time, empirically perfect approximations is a viable and powerful paradigm, delivering both performance and quality without compromise.
Continual knowledge graph embedding (CKGE) aims to incrementally learn embeddings of entities and relations in a knowledge graph (KG) that evolves over time with a sequence of newly arriving triples. This capability is essential for dynamic applications such as retrieval-augmented generation (RAG), but remains challenging due to the structural diversity and non-uniform growth of evolving KGs. Existing CKGE approaches reveal limitations in both leveraging rich structural information and achieving update efficiency, as they often rely on simplistic metrics (e.g., degree) and a vanilla TransE loss that is not adaptive to structural dynamics. In this work, we propose STARK (Structure-aware and Adaptive Representation learning for CKGE), a fast yet effective CKGE framework that enhances structure awareness and supports adaptive optimization. To this end, we propose two major techniques, namely structural novelty prioritization (SNP) and adaptive TransE loss (ATL). Through SNP, STARK allocates higher representational capacity to topologically more important entities, while ATL adaptively keeps embeddings close to the true target of each head-relation pair (h, r, ?), dynamically scaling the boundary according to the cardinality of candidate tails. Extensive experiments on multiple CKGE benchmarks demonstrate that STARK achieves both higher accuracy and better efficiency in the time-performance tradeoff compared to existing state-of-the-art methods. Moreover, embedding visualizations and quantitative analysis confirm that STARK produces more coherent clusters of entities sharing the same (h, r, ?), reflecting improved structural consistency.
While the web interfaces of remotely managed devices offer convenience, their unstructured content can inadvertently leak geographic locations, posing a significant security risk. We aim to assess the feasibility of automatically exploiting this leakage, serving as a clear warning to cybersecurity regulators. To this end, we propose WebGeoInfer, a framework that does not rely on page structure. It extracts clues through page clustering and differential analysis to overcome the challenge of information heterogeneity. It also leverages search engines and large language models to augment sparse clues and infer precise coordinates, addressing the challenge of information sparsity. In large-scale experiments, WebGeoInfer successfully located 5,435 devices across 94 countries and 2,056 cities, achieving accuracy rates as high as 96.96% at the country level, 88.05% at the city level, and 79.70% at the street level. These findings provide the first conclusive evidence of the reality and scale of this threat. Furthermore, our analysis offers new insights and mitigation strategies for affected devices, establishing a key benchmark for future security research.
The InterPlanetary File System (IPFS) is the largest decentralized content-centric storage network. While its architecture enables resilient, distributed content delivery, it can be abused to host and disseminate malicious content. Public IPFS HTTP gateways further expand this threat surface, enabling attackers to deploy phishing websites and leverage gateway reputation to evade detection. This model can keep content available even after attackers go offline and challenges traditional phishing detection systems. We present a framework for monitoring and characterizing phishing on IPFS, leveraging a measurement platform that integrates multi-source data, including IPFS traffic and passive DNS. Over 11 months, we detect 10,489 phishing CIDs, grouped into 448 phishing clusters. 80% of detected CIDs originate from only 69 clustered campaigns indicating that targeting a small number of dominant clusters could yield high mitigation leverage. We also identify 588 gateways involved in dissemination, including 573 outside public gateway lists, and show that attackers can exploit caching across reputable gateways to amplify attacks and extend content availability. Finally, we find that traditional Web phishing countermeasures and IPFS blocklists provide insufficient protection. Our findings support practical mitigation and offer broader insights for trust and safety in decentralized web infrastructures.
Retrieval-Augmented Generation (RAG) has emerged as a paradigm for enhancing large language models (LLMs) with external knowledge, yet existing graph-based methods face a fundamental limitation: entity-centric and chunk-centric approaches operate on representations anchored to original text without true knowledge fusion. While entity-centric methods connect logically related content and chunk-centric methods preserve context, both retrieve information separately through similarity search, missing emergent understanding from their synthesis. In this paper, we propose HyGRAG, a hierarchical graph RAG framework that transcends source documents by addressing three core challenges: constructing summaries that genuinely integrate contextual and relational information, leveraging these synthesized representations to access emergent knowledge during retrieval, and efficiently updating hierarchical structures for dynamic corpora. Specifically, we design hierarchical index structures over hybrid graphs with both chunk and entity nodes, then iteratively cluster them and generate LLM-based summaries. Then, we design context and relation-aware retrieval that searches across all abstraction levels while expanding through community membership. Moreover, we enable dynamic knowledge update through attachment-based algorithms with only local re-summarization. Experimental results show that HyGRAG improves the average accuracy of multi-hop reasoning tasks by 9.7%, while maintaining reasonable efficiency.
Cross-modal retrieval (CMR) has advanced considerably by mapping image and text features into a shared embedding space; however, these approaches still face two persistent challenges: (1) semantic sparsity, where discriminative cues are confined to localized regions, making it difficult to identify implicit visual evidence; and (2) ranking uncertainty under semantic ambiguity, where models struggle to maintain the correct retrieval order when candidates share similar contexts. To address these issues, we propose the Dual-Branch Multi-Granularity Network (DBMG) with Structured Contrastive Ranking, which enriches visual semantics by leveraging a multimodal large language model to generate auxiliary descriptions, aligns sparse cues through a dual-branch architecture capturing both global and local interactions, and enforces ranking consistency via a three-stage contrastive objective that progressively optimizes category clustering, instance alignment, and margin-based ranking. Extensive experiments on four standard CMR benchmarks demonstrate that DBMG outperforms 12 strong baselines, achieving an average 15.91% improvement in mAP, establishing a new state-of-the-art. The code is available at https://github.com/DMiC-Lab-HFUT/DBMG.
Text-based Person Retrieval (TPR) aims to retrieve specific pedestrian images from a gallery based on the given textual descriptions, serving as a fine-grained instance of cross-modal retrieval on the Web. Current mainstream approaches primarily leverage pre-trained models and attention mechanisms to enhance multi-modal representations. Despite notable progress, they still struggle with two major challenges: 1) Intra-instance semantic asymmetry, which mainly derives from the partial semantic relevance conveyed by each image-text pair; and 2) Inter-instance semantic ambiguity, which arises from the high similarity of image-text pairs with different identities. These issues result in suboptimal semantic alignment and degraded retrieval accuracy. To this end, we propose a novel Pedestrian-Centric Discriminative and Fine-grained Semantic Mining (DFSM) framework for TPR. Specifically, our DFSM method comprises two essential components: 1) Text-aware Visual Refinement (TVR), which mitigates visual redundancy by selecting semantically relevant patches under textual guidance, and refines them via adaptive clustering and merging; 2) Token-level Semantic Alignment (TSA), which formulates the matching relationship between image regions and text words as a conditional transport (CT) problem, effectively mining fine-grained semantic differences and enhancing instance discrimination. Extensive experiments on four benchmarks validate the advantages of DFSM in terms of retrieval accuracy and visual interpretability.
Temporal Betweenness Centrality (TBC) measures how often a node appears on optimal temporal paths, reflecting its importance in temporal networks. However, exact computation is highly expensive, and real-world TBC distributions are extremely imbalanced, causing learning-based models to overfit to zero-centrality nodes and fail to identify truly central nodes. Existing graph neural networks (GNNs) either ignore temporal dependencies or cannot handle such extreme imbalance. To address these issues, we propose CLGNN, a scalable and inductive contrastive learning-based GNN for accurate TBC prediction. CLGNN preserves temporal path validity through an instance graph and encodes structural, path-time aware dependencies via dual aggregation. To mitigate imbalance, a stability-based clustering-guided contrastive module separates nodes of different centrality levels in representation space, while a regression head estimates TBC values. Extensive experiments on diverse benchmarks demonstrate that CLGNN is scalable, generalizable, and effective.
Current contrastive graph clustering approaches suffer from insufficient integration of structural and semantic information, coupled with the absence of reliable sample selection strategies. To address these dual limitations, we introduce Structure-Semantic Synergized Deep Contrastive Graph Clustering (S³-DCGC), a novel framework that jointly models topological structure and semantic features through two synergistic mechanisms. First, a structure-aware curriculum negative sampling strategy progressively identifies hard negative samples using dynamic-range masking, enhancing discriminative structural learning. Second, a semantic confidence-guided contrastive mechanism quantifies node reliability via composite confidence scores—integrating cluster affinity and cross-view consistency—to select high-confidence positive/negative pairs. Dynamically coordinated by a soft-alignment strategy that shifts optimization focus from structural to semantic dominance during training, these components achieve balanced synergy. Comprehensive experiments conducted on five benchmark datasets demonstrate S³-DCGC's superiority, achieving significant performance gains. Ablation studies and visual analyses further corroborate the critical importance of structure-semantic synergy in achieving robust clustering performance.
Contrastive learning has demonstrated strong performance in attributed hypergraph clustering. Typically, existing methods based on contrastive learning first learn node embeddings and then apply clustering algorithms, such as k-means, to these embeddings to obtain the clustering results.However, these methods lack direct clustering supervision, risking the inclusion of clustering-irrelevant information in the learned graph. To this end, we propose a Contrastive learning approach for Attributed Hypergraph Clustering (CAHC), an end-to-end method that simultaneously learns node embeddings and obtains clustering results. CAHC consists of two main steps: representation learning and cluster assignment learning. The former employs a novel contrastive learning approach that incorporates both node-level and hyperedge-level objectives to generate node embeddings.The latter joint embedding and clustering optimization to refine these embeddings by clustering-oriented guidance and obtains clustering results simultaneously.Extensive experimental results demonstrate that CAHC outperforms baselines on eight datasets.
Graph clustering aims to partition nodes into distinct clusters based on their similarity, thereby revealing relationships among nodes. Nevertheless, most existing methods do not fully utilize these edge weights. Leveraging edge weights in graph clustering tasks faces two critical challenges. (1) The introduction of edge weights may significantly increase storage space and training time, making it essential to reduce the graph scale while preserving nodes that are beneficial for the clustering task. (2) Edge weight information may inherently contain noise that negatively impacts clustering results. However, few studies can jointly optimize clustering and edge weights, which is crucial for mitigating the negative impact of noisy edges on clustering task. To address these challenges, we propose a contractile edge-weight-aware graph clustering network. Specifically, a cluster-oriented graph contraction module is designed to reduce the graph scale while preserving important nodes. An edge-weight-aware attention network is designed to identify and weaken noisy connections. In this way, we can more easily identify and mitigate the impact of noisy edges during the clustering process, thus enhancing clustering effectiveness. We conducted extensive experiments on three real-world weighted graph datasets. In particular, our model outperforms the best baseline, demonstrating its superior performance. Furthermore, experiments also show that the proposed graph contraction module can significantly reduce training time and storage space.
Social event detection (SED) enhances public awareness by clustering large-scale social messages and has been widely applied across diverse domains. While many existing frameworks adopt Graph Convolution Networks (GCN) as backbones and extend them with auxiliary modules to model complex message relationships, they rarely explore the deeper potential of GCN itself. Specifically, the core operation of GCN—smoothed feature aggregation—implicitly assumes that social information diffusion follows a single-pass and independent heat propagation process. However, real-world diffusion is inherently multi-wave and oscillatory, where different messages interact through reinforcement and interference, resembling the principle of wave–particle duality. To address this gap, we propose Physics-Inspired Graph Convolution Networks (PIGCN ), a novel model that unifies wave-based propagation and particle-like interactions. Specifically, PIGCN integrates a Helmholtz Graph Filter module to capture spectral wave propagation with oscillatory dynamics, and a Physical Interaction Force mechanism to adaptively adjust edge weights by attracting messages within the same event and repelling those across events. Building on PIGCN, we further incorporate a contextualized text encoder and timestamp encoding to form a comprehensive SED framework. Extensive experiments demonstrate that PIGCN effectively outperforms conventional GCN baselines and achieves superior performance across multiple SED datasets, establishing a new benchmark for balancing architectural simplicity with effectiveness. Our code can be found on GitHub . https://github.com/yuyongsheng1990/PIGCN
Federated graph-level clustering (FGC) provides an effective solution for analyzing decentralized graph data with privacy protection. Existing methods typically assume that all clients have the same number of clusters. This assumption simplifies the learning task and has achieved preliminary success. However, this assumption rarely holds in practice, as clients often exhibit substantial heterogeneity in both data distributions and semantic granularity. As a result, cluster-specific knowledge becomes misaligned during server-side aggregation, which ultimately degrades the overall clustering performance. To address this challenge, we propose a novel Federated Graph Clustering under Inter-Client Cluster Number Discrepancy (FedCND) framework, which aligns inter-client heterogeneous distributions by decoupling graph data into public and private patterns. Specifically, after initial local training and clustering on each client, we design a public learner and a private learner to model public and private graph data, respectively. Only anonymized, cluster-level public information is uploaded to the server, while private information remains local. On the server, cluster-level public prototypes are aggregated based on affinities between reconstructed cluster-level graphs, enabling privacy-preserving prototype alignment across clients with heterogeneous cluster numbers and mitigating interference from misaligned information during global aggregation. Finally, private subgraphs derive client-specific prototypes through local relearning, which are subsequently fused with globally oriented public prototypes for better clustering. Extensive experiments demonstrate that the proposed FedCND achieves an average of 4.9% accuracy improvement against current state-of-the-art methods.
Clustering is a fundamental task in graph data mining, including both node-level and graph-level clustering. While the former has been extensively explored to capture local structures and features, the latter has gained attention for its ability to capture global relationships and high-level abstractions. However, existing methods often address these two tasks in isolation, which not only wastes computational resources but also fails to fully leverage the knowledge from both levels to improve each other, hindering consistent performance improvement. To this end, we propose a novel Unified Graph Clustering Network called UGCN, which employs both local and global graph information to address node- and graph-level clustering collaboratively. In detail, we design a dual-branch projector that performs joint learning at both node and graph levels. The first branch extracts node-level features and projects them into distinct cluster layers, where the derived prototypes are used to refine graph attributes and highlight clustering-friendly substructures. In parallel, the second branch captures subgraph embeddings and aggregates them into discriminative graph-level representations. we align the two branches through joint contrastive objectives to establish a bidirectional interaction: refined prototypes guide subgraph and graph-level clustering, while graph-level pseudo-labels provide feedback to enhance node-level clustering. Extensive experimental results across seven datasets demonstrate that our method significantly outperforms existing state-of-the-art approaches.
Large Language Models (LLMs) have shown significant potential in handling text-attributed graphs (TAGs). Nevertheless, existing LLM-enhanced approaches for TAG learning mainly utilize LLMs as text augmenters, which not only incur substantial computational overhead but may also introduce noise. In contrast, their capacity as embedding generators remains underutilized. Furthermore, most current methods are designed for specific TAG instances and lack cross-domain transferability. To overcome these limitations, we propose UTAG, a novel framework that leverages LLMs as unified embedding generators. First, we design a dual-view contrastive fine-tuning approach for cross-domain pretraining. The in-domain view promotes local consistency via adaptive positive sample selection, while the cross-domain view establishes alignment through subspace clustering-based cross-domain prototype aggregation. By jointly pretraining on multiple TAG datasets from diverse domains, we obtain a unified LLM encoder that produces transferable representations. Subsequently, we introduce a graph-specific adaptation training technique that implements two-stage dimensionality reduction with carefully designed semantic and Laplacian reconstruction constraints. This allows effective incorporation of structural signals while preserving semantic information to the greatest extent. Additionally, we employ cross-space alignment to further enhance consistency. Extensive experiments demonstrate that UTAG substantially surpasses existing LLM-enhanced methods, achieving an average improvement of 5.9% on cross-domain transfer tasks, which verifies its effectiveness and superiority.