Advanced Graph Neural Networks

Derniers papiers

• Context-aware Entity-Relation Extraction for Threat Intelligence Knowledge Graphs

  Inoussa Mouiche, sherif Saad · 18 mai 2026

  Cybersecurity Knowledge Graphs (CKGs) unify diverse Cyber Threat Intelligence (CTI) sources into structured, queryable formats, offering scalable solutions for automating proactive and real-time security responses. Their increasing adoption has significantly enhanced the workflow and decision-making…

• CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

  Peiyuan Li, Yongqi Huang, Jitao Zhao, Dongxiao He, Di Jin, Weixiong Zhang · 18 mai 2026

  Heterogeneous Graph Prompt Learning (HGPL)has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream applications in heterogeneous graph settings. However, existing HGPL methods are primarily designed for in-domain scenarios…

• T2T-LA: A Topology-to-Topology LLM Agent for Graph Learning with Neither Feature Access nor Task Knowledge

  Yongyu Wang · 18 mai 2026

  Graph learning aims to convert data into graph representations, which are fundamental to many problems in machine learning for CAD, where circuits, layouts, designs, and optimization states are often modeled as graph-structured objects. Existing graph learning methods usually rely on carefully desig…

• A Differentiable Measure of Algebraic Complexity: Provably Exact Discovery of Group Structures

  Dongsung Huh, Lior Horesh, Halyun Jeong · 18 mai 2026

  Discovering discrete algebraic rules from data is a fundamental challenge in machine learning. We formalize this problem through Cayley-table completion -- an algebraic counterpart to classical matrix completion -- where the degree of associativity violation replaces linear rank as the intrinsic mea…

• Logical Grammar Induction via Graph Kolmogorov Complexity: A Neuro-Symbolic Framework for Self-Healing Clinical Data Integrity

  Abolfazl Zarghani, Amir Malekesfandiari · 18 mai 2026

  The reliability of Healthcare Information Systems (HIS) is frequently compromised by human-induced data entry errors, which existing statistical anomaly detection methods fail to distinguish from legitimate clinical extremes. This paper proposes Logic-GNN, a novel neuro-symbolic framework that treat…

• Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks

  Jingcheng Wu, Ratan Bahadur Thapa, Mojtaba Nayyeri, Lucas Etteldorf, Max Finkenbeiner, Fabian Leeske, Steffen Staab · 18 mai 2026

  Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as conventional approaches flatten databases into single tables via manual feature engineerin…

• GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective

  Xu Wang, Xunkai Li, Yinlin Zhu, Rong-Hua Li, Guoren Wang · 18 mai 2026

  Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes and edges encode corpus structure, provide a natural settin…

• Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers

  Yang Li · 18 mai 2026

  As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for efficient and effective deployment. While recent methods rely on complex learned routing strategies, their dependence on disparate training data and evaluat…

• Gaussian Relational Graph Transformer

  Zezhong Ding, Jin Li, Xugang Wang, Xike Xie · 18 mai 2026

  Relational graph learning models relational databases as graphs and has demonstrated superior performance on a wide range of relational predictive tasks. However, existing methods struggle to capture long-range dependencies due to information decay in their message-passing mechanisms, and recent rel…

• SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch

  Zhantao Wang · 18 mai 2026

  Multi-agent orchestration frameworks such as LangChain, LangGraph, and CrewAI route tasks through graph-based pipelines but do not enforce the stage constraints that govern real business processes. We present SDOF, a framework that treats multi-agent execution as a constrained state machine. SDOF op…

• Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix

  Jinhao Zhang, Kangfei Zhao, Qiuhao Zeng, Long-Kai Huang · 18 mai 2026

  Transformer-based architectures have become the dominant paradigm for Continuous-Time Dynamic Graph (CTDG) learning, yet their performance remains limited on temporally shifted datasets. In this work, we identify attention dispersion as a shared failure mode of dynamic graph Transformers under tempo…

• OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

  Louisa Cornelis, Johan Mathe, Louis Van Langendonck, Guillermo Bern\'ardez, Nina Miolane · 18 mai 2026

  Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime $n \gg p$, where the number of graphs $n$ greatly exceeds the number of nodes per graph $p$. This overlooks biological domains such as omics, which operate in t…

• GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning

  Yan Jiang, Ruihong Qiu, Zi Huang · 15 mai 2026

  Graph prompt tuning has shown great potential in graph learning by introducing trainable prompts to enhance the model performance in conventional single-domain scenarios. Recent research has extended graph prompts to improve Graph Foundation Models (GFMs) by few-shot tuning auxiliary prompts. Despit…

• Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology

  Jesseba Fernando, Grigori Guitchounts · 15 mai 2026

  Large language models are remarkably capable, yet how computation propagates through their layers remains poorly understood. A growing line of work treats depth as discrete time and the residual stream as a dynamical system, where each layer's nonlinear update has a local linear description. However…

• Compositional Sparsity as an Inductive Bias for Neural Architecture Design

  Hongyu Lin, Antonio Briola, Yuanrong Wang, Tomaso Aste · 15 mai 2026

  Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning is driven by compositional sparsity, where target functions d…

• Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective

  Peiyao Wang, Liang Bai, Xian Yang, Richard Yi Da Xu, Jiye Liang · 14 mai 2026

  Graph neural networks (GNNs) have emerged as a fundamental tool for learning from graph-structured data, achieving strong performance across a wide range of applications. However, understanding their generalization capabilities remains challenging due to the complex structural dependencies inherent …

• EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild

  Yuyang Dai, Zheng Chen, Jathurshan Pradeepkumar, Yasuko Matsubara, Jimeng Sun, Yasushi Sakurai, Yushun Dong · 14 mai 2026

  Epilepsy diagnosis and treatment require evidence-intensive reasoning across heterogeneous clinical knowledge, including biosignal patterns, genetic mechanisms, pharmacogenomics, treatment strategies, and patient outcomes. In this work, we present \textsc{EpiGraph}, a large-scale epilepsy knowledge …

• MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing

  Chaokai Wu, Haofu Shi, Ningxuan Ma, Jianghong Ma, Xiaofeng Zhang · 14 mai 2026

  Graph Neural Networks (GNNs) suffer from over-squashing in deep message passing, where information from exponentially growing neighborhoods is compressed into fixed-dimensional representations. We show that this issue becomes a distinct failure mode in multi-label graphs: neighboring nodes often sha…

• A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions

  Mohamed Mahmoud Amar, Nairouz Mrabah, Mohamed Bouguessa, Abdoulaye Banir\'e Diallo · 14 mai 2026

  Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing methods still predominantly focus on a single graph abstractio…

• The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks

  Fengqing Jiang, Yuetai Li, Yichen Feng, Kaiyuan Zheng, Luyao Niu, Bhaskar Ramasubramanian, Basel Alomair, Linda Bushnell, Radha Poovendran · 14 mai 2026

  Hypergraphs provide a natural framework to model higher-order interactions in scientific, social, and biological systems. Hypergraph neural networks (HGNNs) aim to learn from such data, yet it remains unclear which higher-order structures these models can represent. We show that hypergraph expressiv…

• Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents

  Haoran Bu, Litian Zhang, Chuxuan Zhang, Zhanyuan Liu, Hui Pang, Xi Zhang · 14 mai 2026

  Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, while these botnets exhibit realistic local social interactions, they fail to preserve human-like social network. This is b…

• Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification

  Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa · 14 mai 2026

  Existing multiplex graph models often assume homophily, where connected nodes tend to belong to the same class or share similar attributes. Consequently, these models may struggle with graphs exhibiting heterophily, where connected nodes typically belong to different classes and have dissimilar attr…

• What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition

  Danny Wang, Ruihong Qiu, Zi Huang · 14 mai 2026

  Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from eith…

• Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

  Sirui Zhang, Haonan Wang, Xunkai Li, Zekai Chen, Shumeng Li, Hongchao Qin, Rong-Hua Li, Guoren Wang · 14 mai 2026

  Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applications. However, real-world graphs are often isolated due to data-sharing limitations across multiple parties, and their m…

• GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

  Kaixiang Zhao, Bolin Shen, Yuyang Dai, Shayok Chakraborty, Yushun Dong · 14 mai 2026

  Graph neural networks (GNNs) deployed as cloud services can be \emph{stolen} through \emph{model-extraction attacks}, which train a surrogate from query responses to reproduce the target's behaviour, and a growing line of ownership defenses tries to prevent or trace such theft. The title of this pap…