Advanced Graph Neural Networks

Derniers papiers

• Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization

  Gerard Pons, Besim Bilalli, Anna Queralt · 17 novembre 2025

  Many Knowledege Graphs (KGs) are frequently updated, forcing their Knowledge Graph Embeddings (KGEs) to adapt to these changes. To address this problem, continual learning techniques for KGEs incorporate embeddings for new entities while updating the old ones. One necessary step in these methods is …

• GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning

  Ying Song, Balaji Palanisamy · 17 novembre 2025

  Graph unlearning has emerged as a promising solution for complying with "the right to be forgotten" regulations by enabling the removal of sensitive information upon request. However, this solution is not foolproof. The involvement of multiple parties creates new attack surfaces, and residual traces…

• HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings

  Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy, Vaibhav Gandhi · 17 novembre 2025

  Knowledge graphs have emerged as fundamental structures for representing complex relational data across scientific and enterprise domains. However, existing embedding methods face critical limitations when modeling diverse relationship types at scale: Euclidean models struggle with hierarchies, vect…

• Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning

  Jun Hu, Shangheng Chen, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He · 17 novembre 2025

  Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Pre-computation-based HGNNs address this by performing message pa…

• Flow-Attentional Graph Neural Networks

  Pascal Plettenberg, Dominik K\"ohler, Bernhard Sick, Josephine M. Thomas · 17 novembre 2025

  Graph Neural Networks (GNNs) have become essential for learning from graph-structured data. However, existing GNNs do not consider the conservation law inherent in graphs associated with a flow of physical resources, such as electrical current in power grids or traffic in transportation networks, wh…

• Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement

  Yinlin Zhu, Xunkai Li, Jishuo Jia, Miao Hu, Di Wu, Meikang Qiu · 17 novembre 2025

  Recent advances in graph machine learning have shifted to data-centric paradigms, driven by two emerging fields: (1) Federated graph learning (FGL) enables multi-client collaboration but faces challenges from data and task heterogeneity, limiting its practicality; (2) Graph foundation models (GFM) o…

• Hypergraph Neural Network with State Space Models for Node Classification

  A. Quadir, M. Tanveer · 17 novembre 2025

  In recent years, graph neural networks (GNNs) have gained significant attention for node classification tasks on graph-structured data. However, traditional GNNs primarily focus on adjacency relationships between nodes, often overlooking the role-based characteristics that can provide complementary …

• Enhancing Graph Representations with Neighborhood-Contextualized Message-Passing

  Brian Godwin Lim · 17 novembre 2025

  Graph neural networks (GNNs) have become an indispensable tool for analyzing relational data. In the literature, classical GNNs may be classified into three variants: convolutional, attentional, and message-passing. While the standard message-passing variant is highly expressive, its typical pair-wi…

• Heterogeneous Attributed Graph Learning via Neighborhood-Aware Star Kernels

  Hong Huang, Chengyu Yao, Haiming Chen, Hang Gao · 17 novembre 2025

  Attributed graphs, typically characterized by irregular topologies and a mix of numerical and categorical attributes, are ubiquitous in diverse domains such as social networks, bioinformatics, and cheminformatics. While graph kernels provide a principled framework for measuring graph similarity, exi…

• Dynamic Deep Graph Learning for Incomplete Multi-View Clustering with Masked Graph Reconstruction Loss

  Zhenghao Zhang, Jun Xie, Xingchen Chen, Tao Yu, Hongzhu Yi, Kaixin Xu, Yuanxiang Wang, Tianyu Zong, Xinming Wang, Jiahuan Chen, Guoqing Chao, Feng Chen, Zhepeng Wang, Jungang Xu · 17 novembre 2025

  The prevalence of real-world multi-view data makes incomplete multi-view clustering (IMVC) a crucial research. The rapid development of Graph Neural Networks (GNNs) has established them as one of the mainstream approaches for multi-view clustering. Despite significant progress in GNNs-based IMVC, so…

• AdaptViG: Adaptive Vision GNN with Exponential Decay Gating

  Mustafa Munir, Md Mostafijur Rahman, Radu Marculescu · 14 novembre 2025

  Vision Graph Neural Networks (ViGs) offer a new direction for advancements in vision architectures. While powerful, ViGs often face substantial computational challenges stemming from their graph construction phase, which can hinder their efficiency. To address this issue we propose AdaptViG, an effi…

• Efficient quantification on large-scale networks

  Alessio Micheli, Alejandro Moreo, Marco Podda, Fabrizio Sebastiani, William Simoni, Domenico Tortorella · 14 novembre 2025

  Network quantification (NQ) is the problem of estimating the proportions of nodes belonging to each class in subsets of unlabelled graph nodes. When prior probability shift is at play, this task cannot be effectively addressed by first classifying the nodes and then counting the class predictions. I…

• Overlap-aware meta-learning attention to enhance hypergraph neural networks for node classification

  Murong Yang, Shihui Ying, Yue Gao, Xin-Jian Xu · 14 novembre 2025

  Although hypergraph neural networks (HGNNs) have emerged as a powerful framework for analyzing complex datasets, their practical performance often remains limited. On one hand, existing networks typically employ a single type of attention mechanism, focusing on either structural or feature similarit…

• Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners

  Daniel Herbst, Lea Karbeska, Divyanshu Kumar, Akanksha Ahuja, Fatemeh Gholamzadeh Nasrabadi, Fabrizio Frasca · 14 novembre 2025

  While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operating on sequential graph serializations, LLMs can produce different outputs under node reindexing, edge reordering, or formatting changes, raising robustness c…

• Towards Multiple Missing Values-resistant Unsupervised Graph Anomaly Detection

  Jiazhen Chen, Xiuqin Liang, Sichao Fu, Zheng Ma, Weihua Ou · 14 novembre 2025

  Unsupervised graph anomaly detection (GAD) has received increasing attention in recent years, which aims to identify data anomalous patterns utilizing only unlabeled node information from graph-structured data. However, prevailing unsupervised GAD methods typically presuppose complete node attribute…

• GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance

  Chaofan Zhu, Xiaobing Rui, Zhixiao Wang · 14 novembre 2025

  Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations. These methods can be broadly categorized into the data-level and the algorithm-level. The former aims to synthesize mino…

• HyperEvent: A Strong Baseline for Dynamic Link Prediction via Relative Structural Encoding

  Jian Gao, Jianshe Wu, JingYi Ding · 14 novembre 2025

  Learning representations for continuous-time dynamic graphs is critical for dynamic link prediction. While recent methods have become increasingly complex, the field lacks a strong and informative baseline to reliably gauge progress. This paper proposes HyperEvent, a simple approach that captures re…

• A Distributed Training Architecture For Combinatorial Optimization

  Yuyao Long · 13 novembre 2025

  In recent years, graph neural networks (GNNs) have been widely applied in tackling combinatorial optimization problems. However, existing methods still suffer from limited accuracy when addressing that on complex graphs and exhibit poor scalability, since full training requires loading the whole adj…

• Spatio-Temporal Graph Unlearning

  Qiming Guo, Wenbo Sun, Wenlu Wang · 13 novembre 2025

  Spatio-temporal graphs are widely used in modeling complex dynamic processes such as traffic forecasting, molecular dynamics, and healthcare monitoring. Recently, stringent privacy regulations such as GDPR and CCPA have introduced significant new challenges for existing spatio-temporal graph models,…

• LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning

  Sai Puppala, Ismail Hossain, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder · 13 novembre 2025

  We propose a method that uses large language models to assist graph machine learning under personalization and privacy constraints. The approach combines data augmentation for sparse graphs, prompt and instruction tuning to adapt foundation models to graph tasks, and in-context learning to supply fe…

• GMTRouter: Personalized LLM Router over Multi-turn User Interactions

  Encheng Xie, Yihang Sun, Tao Feng, Jiaxuan You · 13 novembre 2025

  Large Language Model (LLM) routing has demonstrated strong capability in balancing response quality with computational cost. As users exhibit diverse preferences, personalization has attracted increasing attention in LLM routing, since even identical queries may require different models to generate …

• Practical and Performant Enhancements for Maximization of Algebraic Connectivity

  Leonard Jung, Alan Papalia, Kevin Doherty, Michael Everett · 13 novembre 2025

  Long-term state estimation over graphs remains challenging as current graph estimation methods scale poorly on large, long-term graphs. To address this, our work advances a current state-of-the-art graph sparsification algorithm, maximizing algebraic connectivity (MAC). MAC is a sparsification metho…

• Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants

  Gangda Deng, Hongkuan Zhou, Rajgopal Kannan, Viktor Prasanna · 13 novembre 2025

  Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs). Increasing the GNN depth can expand the scope (i.e., receptive field), potentially finding homophily from the higher-order neighborhoods. However, GNNs suffer from performance degradation…

• Graph Contrastive Learning for Connectome Classification

  Mart\'in Schmidt, Sara Silva, Federico Larroca, Gonzalo Mateos, Pablo Mus\'e · 13 novembre 2025

  With recent advancements in non-invasive techniques for measuring brain activity, such as magnetic resonance imaging (MRI), the study of structural and functional brain networks through graph signal processing (GSP) has gained notable prominence. GSP stands as a key tool in unraveling the interplay …

• GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases

  Alfred Clemedtson, Borun Shi · 13 novembre 2025

  Large language models have shown remarkable language processing and reasoning ability but are prone to hallucinate when asked about private data. Retrieval-augmented generation (RAG) retrieves relevant data that fit into an LLM's context window and prompts the LLM for an answer. GraphRAG extends thi…