Advanced Graph Neural Networks

Derniers papiers

• LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation

  Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao Huang · 6 avril 2026

  Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering techniques, GraphRAG systems demonstrate inherent resistance to…

• OntoKG: Ontology-Oriented Knowledge Graph Construction with Intrinsic-Relational Routing

  Yitao Li, Zhanlin Liu, Anuranjan Pandey, Muni Srikanth · 6 avril 2026

  Organizing a large-scale knowledge graph into a typed property graph requires structural decisions -- which entities become nodes, which properties become edges, and what schema governs these choices. Existing approaches embed these decisions in pipeline code or extract relations ad hoc, producing s…

• LLM+Graph@VLDB'2025 Workshop Summary

  Yixiang Fang, Arijit Khan, Tianxing Wu, Da Yan, Shu Wang · 6 avril 2026

  The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing strong interest from both academia and industry. The 2nd LLM+Graph Workshop, co-located with the 51st International Conference on Very Large Data Bases (VLDB 2…

• AlertStar: Path-Aware Alert Prediction on Hyper-Relational Knowledge Graphs

  Zahra Makki Nayeri, Mohsen Rezvani · 6 avril 2026

  Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approaches lack the semantic depth required for path reasoning over attacker-victim interactions. We address this by first modelling network alerts as a knowledge graph, then formulating hyper-relati…

• Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network

  Mahdi Tavassoli Kejani, Fadi Dornaika, Charlotte Laclau, Jean-Michel Loubes · 6 avril 2026

  In recent years, Graph Neural Networks (GNNs) have achieved remarkable success in tasks such as node classification, link prediction, and graph representation learning. However, they remain susceptible to biases that can arise not only from node attributes but also from the graph structure itself. A…

• Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

  Cunyang Wei, Siddharth Singh, Aishwarya Sarkar, Daniel Nichols, Tisha Patel, Aditya K. Ranjan, Sayan Ghosh, Ali Jannesari, Nathan R. Tallent, Abhinav Bhatele · 6 avril 2026

  Graph neural networks (GNNs) are widely used for learning on graph datasets derived from various real-world scenarios. Learning from extremely large graphs requires distributed training, and mini-batching with sampling is a popular approach for parallelizing GNN training. Existing distributed mini-b…

• DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation

  Yingxu Wang, Kunyu Zhang, Jiaxin Huang, Mengzhu Wang, Mingyan Xiao, Siyang Gao, Nan Yin · 6 avril 2026

  Graph domain adaptation (GDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph under distribution shifts. However, existing methods are largely feature-centric and overlook structural discrepancies, which become particularly detrimental under significant topology s…

• Universal Hypernetworks for Arbitrary Models

  Xuanfeng Zhou · 3 avril 2026

  Conventional hypernetworks are typically engineered around a specific base-model parameterization, so changing the target architecture often entails redesigning the hypernetwork and retraining it from scratch. We introduce the \emph{Universal Hypernetwork} (UHN), a fixed-architecture generator that …

• Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods

  Avrim Blum, Daniel Hsu, Cyrus Rashtchian, Donya Saless · 3 avril 2026

  Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's parametric knowledge and externally retrieved information. However, the theoretical underpinnings of this relationship remain poorly understood. Specifically, it is …

• Robust Graph Representation Learning via Adaptive Spectral Contrast

  Zhuolong Li, Boxue Yang, Haopeng Chen · 3 avril 2026

  Spectral graph contrastive learning has emerged as a unified paradigm for handling both homophilic and heterophilic graphs by leveraging high-frequency components. However, we identify a fundamental spectral dilemma: while high-frequency signals are indispensable for encoding heterophily, our theore…

• A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware

  Shichang Zhang (Celine), Atefeh Sohrabizadeh (Celine), Cheng Wan (Celine), Zijie Huang (Celine), Ziniu Hu (Celine), Yewen Wang (Celine), Yingyan (Celine), Lin, Jason Cong, Yizhou Sun · 2 avril 2026

  Graph neural networks (GNNs) are emerging for machine learning research on graph-structured data. GNNs achieve state-of-the-art performance on many tasks, but they face scalability challenges when it comes to real-world applications that have numerous data and strict latency requirements. Many studi…

• EmbedPart: Embedding-Driven Graph Partitioning for Scalable Graph Neural Network Training

  Nikolai Merkel, Ruben Mayer, Volker Markl, Hans-Arno Jacobsen · 2 avril 2026

  Graph Neural Networks (GNNs) are widely used for learning on graph-structured data, but scaling GNN training to massive graphs remains challenging. To enable scalable distributed training, graphs are divided into smaller partitions that are distributed across multiple machines such that inter-machin…

• A Cross-graph Tuning-free GNN Prompting Framework

  Yaqi Chen, Shixun Huang, Ryan Twemlow, Lei Wang, John Le, Sheng Wang, Willy Susilo, Jun Yan, Jun Shen · 2 avril 2026

  GNN prompting aims to adapt models across tasks and graphs without requiring extensive retraining. However, most existing graph prompt methods still require task-specific parameter updates and face the issue of generalizing across graphs, limiting their performance and undermining the core promise o…

• Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning

  Ayoub Ghriss · 2 avril 2026

  Probabilistic relaxations of graph cuts offer a differentiable alternative to spectral clustering, enabling end-to-end and online learning without eigendecompositions, yet prior work centered on RatioCut and lacked general guarantees and principled gradients. We present a unified probabilistic frame…

• Is One Token All It Takes? Graph Pooling Tokens for LLM-based GraphQA

  Ankit Grover, Lodovico Giaretta, R\'emi Bourgerie, Sarunas Girdzijauskas · 2 avril 2026

  The integration of Graph Neural Networks (GNNs) with Large Language Models (LLMs) has emerged as a promising paradigm for Graph Question Answering (GraphQA). However, effective methods for encoding complex structural information into the LLM's latent space remain an open challenge. Current state-of-…

• Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts

  Sha Li, Naren Ramakrishnan · 2 avril 2026

  Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors and fixed orchestration strategies, leading to brittle perf…

• Generalization Bounds for Spectral GNNs via Fourier Domain Analysis

  Vahan A. Martirosyan, Daniele Malitesta, Hugues Talbot, Jhony H. Giraldo, Fragkiskos D. Malliaros · 2 avril 2026

  Spectral graph neural networks learn graph filters, but their behavior with increasing depth and polynomial order is not well understood. We analyze these models in the graph Fourier domain, where each layer becomes an element-wise frequency update, separating the fixed spectrum from trainable param…

• Performance Evaluation of LLMs in Automated RDF Knowledge Graph Generation

  Ioana Ramona Martin, Tudor Cioara, Ionut Anghel, Gabriel Arcas · 1 avril 2026

  Cloud systems generate large, heterogeneous log data containing critical infrastructure, application, and security information. Transforming these logs into RDF triples enables their integration into knowledge graphs, improving interpretability, root-cause analysis, and cross-service reasoning beyon…

• Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification

  Guan Wang, Shuyin Xia, Lei Qian, Guoyin Wang, Yi Liu, Yi Wang, Wei Wang · 1 avril 2026

  Graph Convolutional Network (GCN) is a model that can effectively handle graph data tasks and has been successfully applied. However, for large-scale graph datasets, GCN still faces the challenge of high computational overhead, especially when the number of convolutional layers in the graph is large…

• Spectral Higher-Order Neural Networks

  Gianluca Peri, Timoteo Carletti, Duccio Fanelli, Diego Febbe · 31 mars 2026

  Neural networks are fundamental tools of modern machine learning. The standard paradigm assumes binary interactions (across feedforward linear passes) between inter-tangled units, organized in sequential layers. Generalized architectures have been also designed that move beyond pairwise interactions…

• Building evidence-based knowledge graphs from full-text literature for disease-specific biomedical reasoning

  Chang Zong, Sicheng Lv, Si-tu Xue, Huilin Zheng, Jian Wan, Lei Zhang · 31 mars 2026

  Biomedical knowledge resources often either preserve evidence as unstructured text or compress it into flat triples that omit study design, provenance, and quantitative support. Here we present EvidenceNet, a framework and dataset for building disease-specific knowledge graphs from full-text biomedi…

• CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning

  Xuanze Chen, Jiajun Zhou, Yadong Li, Shanqing Yu, Qi Xuan · 31 mars 2026

  Heterogeneous graph representation learning (HGRL) is essential for modeling complex systems with diverse node and edge types. However, most existing methods are limited to closed-world settings with shared schemas and feature spaces, hindering cross-domain generalization. While recent graph foundat…

• NeiGAD: Augmenting Graph Anomaly Detection via Spectral Neighbor Information

  Qing Qing, Huafei Huang, Mingliang Hou, Renqiang Luo, Mohsen Guizani · 31 mars 2026

  Graph anomaly detection (GAD) aims to identify irregular nodes or structures in attributed graphs. Neighbor information, which reflects both structural connectivity and attribute consistency with surrounding nodes, is essential for distinguishing anomalies from normal patterns. Although recent graph…

• Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books

  Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khanh-Duy Le, Minh-Triet Tran, Tam V. Nguyen, Trung-Nghia Le · 31 mars 2026

  The Four Books have shaped East Asian intellectual traditions, yet their multi-layered interpretive complexity limits their accessibility in the digital age. While traditional bilingual commentaries provide a vital pedagogical bridge, computational frameworks are needed to preserve and explore this …

• TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution

  Yinlin Zhu, Xunkai Li, Di Wu, Wang Luo, Miao Hu, Di Wu · 31 mars 2026

  Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks. However, our empirical analysis reveals inherent topology quality limitations in real-world MAGs, including noisy interactions, missing co…