Advanced Graph Neural Networks

Derniers papiers

• Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

  Lei Zhang, Fubo Sun, Haipeng Yang, Zhong Guan, Likang Wu · 28 mai 2026

  Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals, existing methods still struggle to flexibly capture high-order l…

• Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection

  Zhixing Zuo, Huilin He, Jiasheng Wu, Dawei Cheng · 28 mai 2026

  In recent years, Large Language Models (LLMs) have shown great capability in processing graph tasks such as fraud detection. However, most existing methods rely heavily on rich text attributes, which poses difficulties for this domain due to the lack of textual data. Although some pioneering methods…

• Metric-Aware PCA as a Linear Instance of Geometric Deep Learning

  Michael Leznik · 28 mai 2026

  Geometric deep learning organises neural architectures around the symmetries of their data domain, with the choice of symmetry group serving as a geometric prior that determines what representations can be learned. Metric-Aware Principal Component Analysis (MAPCA) parameterises principal component a…

• A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks

  Nicolas Tremblay, Benjamin Ricaud, Filippo Maria Bianchi · 28 mai 2026

  We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which node features and which aspects of the graph topology were leveraged for prediction. In practice, the layer's propagation matrix takes the closed-fo…

• AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems

  Nicole Koenigstein · 28 mai 2026

  Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how roles should interact, when to use retrieval or verificatio…

• Revealing Algorithmic Deductive Circuits for Logical Reasoning

  Phuong Minh Nguyen, Tien Huu Dang, Naoya Inoue · 28 mai 2026

  Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in few-shot learning settings. However, it remains unclear how LLMs…

• FD-RAG: Federated Dual-System Retrieval-Augmented Generation

  Tianhao Gao, Kai Yang, Yiyang Li · 28 mai 2026

  Retrieval-augmented generation (RAG) has emerged as a paradigm for grounding large language models in external knowledge, yet most existing RAG systems assume centralized knowledge access and ample computation. These assumptions break down in edge environments, where knowledge is fragmented across d…

• Revisiting Graph Autoencoders as Implicit Contrastive Learners

  Jintang Li, Ruofan Wu, Yuchang Zhu, Huizhe Zhang, Zulun Zhu, Liang Chen · 28 mai 2026

  Graph autoencoders (GAEs) and graph contrastive learning (GCL) are two major paradigms for self-supervised representation learning on graphs, yet they are often studied in isolation and treated as fundamentally different approaches. In this work, we revisit GAEs through the lens of contrastive learn…

• T-GINEE: A Tensor-Based Multilayer Graph Representation Learning

  Maolin Wang, Ziting Mai, Xuhui Chen, Zhiqi Li, Tianshuo Wei, Yutian Xiao, Wenlin Zhang, Wanyu Wang, Ruocheng Guo, Haoxuan Li, Zenglin Xu, Xiangyu Zhao · 28 mai 2026

  Traditional network analysis focuses on single-layer networks, real-world systems often form multilayer networks with multiple relationship types. However, existing methods typically fail to capture complex inter-layer dependencies by treating layers independently or aggregating them. To address thi…

• Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China

  Hiroto Fukada, Takayuki Mizuno · 28 mai 2026

  Financial and economic research often relies on structured supply-chain disclosures and commercial databases. In China, supplier--customer disclosure is typically limited to major partners of listed firms, leaving unlisted firms and long-tail inter-firm links poorly captured in structured data. Publ…

• Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs

  Safal Thapaliya, Jiatan Huang, Chuxu Zhang · 28 mai 2026

  Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic content, such as paper abstracts, web pages, or product descriptions, large language models (LLMs) can provide low-cost supervision by annotating a smal…

• Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection

  Tairan Huang, Qiang Chen, Yili Wang, Yueyue Ma, Changlong He, Xiu Su, Yi Chen · 28 mai 2026

  Graph anomaly detection aims to identify anomaly nodes in attributed graphs and plays an important role in real-world applications. However, existing graph anomaly detection methods still face two key challenges: 1) fixed pipelines, which restrict their adaptability across different graph tasks unde…

• Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning

  Sridhar Mahadevan · 27 mai 2026

  We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: standard attention is the singleton-neighborhood case, Geometric …

• Generalist Graph Anomaly Detection via Prototype-Based Distillation

  Yiming Xu, Zihan Chen, Zhen Peng, Song Wang, Bin Shi, Bo Dong, Chao Shen · 27 mai 2026

  Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs, has recently gained growing attention. However, existing methods often rely on scarce and costly annotations for trainin…

• ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy

  Xinkui Zhao, Sai Liu, Yifan Zhang, Qingyu Ma, Zewen Lin, Naibo Wang, Guanjie Cheng, Chang Liu, Yueshen Xu · 27 mai 2026

  Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We pro…

• Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks

  Derek Regier, Andrew Polyak, Aresh Dadlani, Khosro Salmani · 27 mai 2026

  Temporal signed networks (TSNs) model the time evolution of cooperative and adversarial relationships that arise in applications such as social media analysis, trust and reputation systems, and financial transaction networks. While graph neural networks (GNNs) perform well for static or unsigned lin…

• Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks

  Zhishuai Guo, Wenhan Wu, Chen Chen, Lei Zhang, Olivera Kotevska, Ravi K Madduri · 27 mai 2026

  Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to privacy and policy constraints. Existing federated GNN methods either ignore cross-client links, leading to degraded accuracy…

• RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections

  Yali Fink, Ido Ben-Yair, Lars Ruthotto, Eran Treister · 27 mai 2026

  The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers optimal linear scaling, its performance is severely constrained by the trade-off between the sparsity and convergence quality of coarse-grid operato…

• Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification

  Pedro Henrique da Costa Avelar, Anderson R. Tavares, Lu\'is C. Lamb · 27 mai 2026

  Superpixel-based image classification has traditionally leveraged graph neural networks (GNNs) for processing irregular image representations. Recent advances in computer vision, driven by Vision Transformers (ViTs), have introduced new paradigms in self-attentional models, surpassing convolutional …

• Learning Dynamic Graph Representations through Timespan View Contrasts

  Yiming Xu, Zhen Peng, Bin Shi, Xu Hua, Bo Dong · 27 mai 2026

  The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological properties within static graphs to create self-supervised signals, neglecting the temporal components carried by real-world …

• GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought

  Weijiang Lv, Wentong Zhao, Jiayu Wang, Yuhao Wu, Jiaheng Wei, Xiaobo Xia · 27 mai 2026

  Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faithfulness assessment methods are either unscalable, expensive, or unreliable. We p…

• Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs

  Yunbo Long, Haolang Zhao, Ge Zheng, Alexandra Brintrup · 27 mai 2026

  LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search and textual reasoning. However, many critical information tasks in supply chains are not simple one-shot queries: they are structural inference prob…

• Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation

  Chengcan Wu, Zhixin Zhang, Mingqian Xu, Zeming Wei, Meng Sun · 27 mai 2026

  Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthiness concerns: adversarial agents can inject misleading information that propagates contagiously through the system, cor…

• GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training

  Yuyang Bai, Zhuofeng Li, Ping Nie, Jianwen Xie, Yu Zhang · 27 mai 2026

  Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organized as heterogeneous graphs rather than plain text. Reasoning over such graphs requires models to follow schema-defined relations through precise function calls…

• Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling

  Andrea Ceni, Alessio Gravina, Claudio Gallicchio, Davide Bacciu, Carola-Bibiane Schonlieb, Moshe Eliasof · 27 mai 2026

  The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, existing GSSMs operate by applying SSM modules to sequences extracted from graphs, often compromising core properties such …