Advanced Graph Neural Networks

Derniers papiers

• Fractal Graph Contrastive Learning

  Nero Z. Li, Xuehao Zhai, Zhichao Shi, Boshen Shi, Xuhui Jiang · 13 mai 2026

  Graph Contrastive Learning (GCL) relies on semantically consistent graph augmentations, but common local perturbations provide limited control over global structural consistency, motivating a more principled global augmentation strategy. We therefore propose Fractal Graph Contrastive Learning (Fract…

• STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

  Zekai Chen, Xun Wu, Xunkai Li, Yihan Sun, Rong-Hua Li, Guoren Wang · 13 mai 2026

  Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node attributes such as text and images, multimodal federated graph learning (MM-FGL) has become an important yet substantially harder setting. The key c…

• CORE: Cyclic Orthotope Relation Embedding for Knowledge Graph Completion

  Yingqi Zeng, Luying Wang, Huiling Zhu · 13 mai 2026

  Knowledge graph completion (KGC) aims to automatically infer missing facts in multi-relational data by mapping entities and relations into continuous representation spaces. Recent region-based embedding models have shown great promise in capturing complex logical patterns by representing relations a…

• Task-Adaptive Embedding Refinement via Test-time LLM Guidance

  Ariel Gera, Shir Ashury-Tahan, Gal Bloch, Ohad Eytan, Assaf Toledo · 13 mai 2026

  We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user query using feedback from a generative LLM on a small set of d…

• A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning

  Haibo Chen, Xin Wang, Jiaheng Chao, Ling Feng, Wenwu Zhu · 13 mai 2026

  Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large Language Models (LLMs) through alignment instruction tuning has become a mainstream paradigm for constructing Graph Language Models (GLMs), combining the generalization ability of LLMs wit…

• Estimating Subgraph Importance with Structural Prior Domain Knowledge

  Changhyun Kim, Seunghwan An, Jong-June Jeon · 13 mai 2026

  We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independe…

• Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation

  Md Sazzad Hossen, Avimanyu Sahoo · 13 mai 2026

  Graphs with heterophily, where adjacent nodes carry different labels, are prevalent in real-world applications, from social networks to molecular interactions. However, existing spectral Graph Neural Network (GNN) approaches tailored for heterophilous graph classification suffer from hub-dominated (…

• SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation

  Luke James Miller, Yugyung Lee · 13 mai 2026

  Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class imbalance -- dense, full-resolution inference scales poorly and forces most pipelines to rely on fixed regionization or downsampling, coupling computa…

• NOFE -- Neural Operator Function Embedding

  Lars Uebbing, Harald L. Joakimsen, Siyan Chen, Georgios Leontidis, Kristoffer K. Wickstr{\o}m, Michael C. Kampffmeyer, S\'ebastien Lef\`evre, Arnt-B{\o}rre Salberg, Robert Jenssen · 13 mai 2026

  Most dimensionality reduction methods treat data as discrete point clouds, ignoring the continuous domain structure inherent to many real-world processes. To bridge this gap, we introduce Neural Operator Function Embedding (NOFE), a domain-aware framework for continuous dimensionality reduction. NOF…

• Approximation of Maximally Monotone Operators : A Graph Convergence Perspective

  Takashi Furuya, Yury Korolev, Takaharu Yaguchi · 13 mai 2026

  Operator learning has been highly successful for continuous mappings between infinite-dimensional spaces, such as PDE solution operators. However, many operators of interest-including differential operators-are discontinuous or set-valued, and lie outside classical approximation frameworks. We propo…

• Random-Set Graph Neural Networks

  Tommy Woodley, Shireen Kudukkil Manchingal, Matteo Tolloso, Davide Bacciu, Fabio Cuzzolin · 13 mai 2026

  Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of the data is a huge mit…

• From Message-Passing to Linearized Graph Sequence Models

  Jo\"el Mathys, Basil Rohner, Saku Peltonen, Roger Wattenhofer · 13 mai 2026

  Message-passing based approaches form the default backbone of most learning architectures on graph-structured data. However, the rapid progress of modern deep learning architectures in other domains, particularly sequence modeling, raises the question of how graph learning can benefit from these adv…

• CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation

  Daohan Su, Hao Liu, Xunkai Li, Yinlin Zhu, Xiong Yongfu, Yi Liu, Hongchao Qin, Rong-Hua Li, Guoren Wang · 13 mai 2026

  Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs, yet most existing approaches rely on tightly coupled architectures that suffer from prohibitive computational overhead. In this paper, we present a systematic empirical analysis showi…

• FERA: Uncertainty-Aware Federated Reasoning for Large Language Models

  Ruhan Wang, Chengkai Huang, Zhiyong Wang, Junda Wu, Rui Wang, Tong Yu, Julian McAuley, Lina Yao, Dongruo Zhou · 13 mai 2026

  Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across organizations that cannot centralize it due to regulatory, proprietary, or institutional constraints. We study federated reasoning, where a server …

• Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion

  Arif D\"onmez, Axel Mosig, Ellen Fritsche, Katharina Koch · 13 mai 2026

  Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians whose learned restriction maps define a task-adapted geometry. While the diffusion limit of NSD is known to be the space of global sections, the representation-th…

• BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts

  Xiaoting Lyu, Yufei Han, Hangwei Qian, Haoyuan Yu, Xiang Ao, Bin Wang, Chenxu Wang, Xiaobo Ma, Wei Wang · 13 mai 2026

  Recent knowledge graph (KG)-enhanced large language models (LLMs) move beyond purely textual knowledge augmentation by encoding retrieved subgraphs into continuous soft prompts via graph neural networks, introducing a graph-conditioned channel that operates alongside the standard text interface. How…

• Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models

  Nikolaos Nakis, Panagiotis Promponas, Konstantinos Tsirkas, Katerina Mamali, Eftychia Makri, Leandros Tassiulas, Nicholas A. Christakis · 13 mai 2026

  Graph representation learning has become a standard approach for analyzing networked data, with latent embeddings widely used for link prediction, community detection, and related tasks. Yet a basic design choice, the latent dimension, is still treated as a brittle hyperparameter, fixed before train…

• Reconnecting Fragmented Citation Networks with Semantic Augmentation

  Vu Thi Huong, Annika Buchholz, Imene Khebouri, Thorsten Koch, Tim Kunt, Wolfgang Peters-Kottig, Tomasz Stompor, Janina Zittel · 13 mai 2026

  Citation graphs are fundamental tools for modeling scientific structure, but are often fragmented due to missing citations of scientifically connected articles. To address this issue, we propose a computationally efficient hybrid framework integrating citation topology with large language model (LLM…

• Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection

  Yingjie Zhou, Yuqin Xie, Fanxing Liu, Dongjin Song, Ce Zhu, Lingqiao Liu · 13 mai 2026

  Weakly supervised graph anomaly detection aims to unveil unusual graph instances, e.g., nodes, whose behaviors significantly differ from normal ones, given only a limited number of annotated anomalies and abundant unlabeled samples. A major challenge is to learn a meaningful latent feature represent…

• Attention-based graph neural networks: a survey

  Chengcheng Sun, Chenhao Li, Xiang Lin, Tianji Zheng, Fanrong Meng, Xiaobin Rui, Zhixiao Wang · 12 mai 2026

  Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topological structures. In recent years, attention mechanism, which is brilliant in the fields of natural language processing and computer vision, is introduced…

• Belief or Circuitry? Causal Evidence for In-Context Graph Learning

  Katharine Kowalyshyn, Timothy Duggan, Daniel Little, Michael C Hughes · 12 mai 2026

  How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random-walk across two competing graph structures. This task's answer is, in principle, decidable: either the model tracks global topology, or it copies l…

• SDG-MoE: Signed Debate Graph Mixture-of-Experts

  Stepan Kulibaba, Kirill Labzin, Artem Dzhalilov, Roman Pakhomov, Oleg Svidchenko, Alexander Gansnikov, Aleksei Shpilman · 12 mai 2026

  Sparse MoE models achieve a good balance between capacity and compute by routing each token to a small subset of experts. However, in most MoE architectures, once a token is routed, the selected experts process it independently and their outputs are combined via a weighted sum. This leaves open whet…

• Improving Generalization by Permutation Routing Across Model Copies

  Shuhei Kashiwamura, Timothee Leleu · 12 mai 2026

  We introduce a use of the \(M\)-cover (or \(M\)-layer) transform for machine learning. The method replicates a model \(M\) times, but instead of coupling the copies through parameter averaging or an explicit attractive force, as in replicated SGD or Elastic SGD, it rewires the contexts in which loca…

• EpiGraph: A Knowledge Graph and Benchmark for Evidence-Intensive Reasoning in Epilepsy

  Yuyang Dai, Zheng Chen, Jathurshan Pradeepkumar, Yasuko Matsubara, Jimeng Sun, Yasushi Sakurai, Yushun Dong · 12 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 …

• PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering

  Shengxiang Gao, Chao Lei, Jey Han Lau, Jianzhong Qi · 12 mai 2026

  Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent KGQA methods mainly follow the retrieval-augmented generation paradigm to ground Large Language Models~(LLMs) with structured knowledge from KGs. However, training effective model…