Advanced Graph Neural Networks

Derniers papiers

• Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach

  Zhengyu Wu, Hongchao Qin, Xunkai Li, Zekai Chen, Rong-Hua Li, Guoren Wang · 19 juin 2026

  MultiModal Federated Graph Learning (MM-FGL) offers a natural collaborative training paradigm, but its practical deployment is challenged by two granularities of modality imbalance. Client-level imbalance occurs when certain clients lack entire modalities, while node-level imbalance occurs when indi…

• The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups

  Przemyslaw Musialski · 19 juin 2026

  We place the attention token on the group: a token is an element $g_i$ of a matrix Lie group $G$ -- a bare transformation, with no feature payload and no external action $\rho(g)$ carrying it. To our knowledge this is the first attention construction whose tokens are bare matrix Lie group elements: …

• Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

  Jiaqing Chen, Zidu Yin, Yichao Cai, Yuhang Liu, Zhen Zhang, Dong Gong, Javen Qinfeng Shi · 19 juin 2026

  Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings. This challenge is most acute for nodes near c…

• Toward General Digraph Contrastive Learning: A Dual Spatial Perspective

  Zhengyu Wu, Daohan Su, Yang Zhang, Xunkai Li, Rong-Hua Li, Guoren Wang · 19 juin 2026

  Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information. However, existing methods predominantly focus on undirected graphs, disregarding the pivotal directional information that is fundamental and indi…

• HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data

  Fang Wang, Paolo Ceravolo, Ernesto Damiani · 19 juin 2026

  We propose HGCN(O), a self-tuning toolkit using Graph Convolutional Network (GCN) models for event sequence prediction. Featuring four GCN architectures (O-GCN, T-GCN, TP-GCN, TE-GCN) across the GCNConv and GraphConv layers, our toolkit integrates multiple graph representations of event sequences wi…

• Implicit Semantic-Aware Communication Based on Hypergraph Reasoning

  Yiwei Liao, Shurui Tu, Yong Xiao, Yingyu Li, Guangming Shi · 19 juin 2026

  Semantic-aware communication has emerged as a transformative paradigm for next-generation communication systems, shifting the fundamental goal from transmitting bit-level symbols to reliably recovering and understanding the semantic meaning of information. Previous studies have demonstrated that rep…

• Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models

  Salim Khazem · 19 juin 2026

  Hallucination detection in large language models (LLMs) is deployment-critical, and recent work shows that the spectrum of attention-derived graph Laplacians carries strong signal about reasoning quality. Prior spectral diagnostics, however, summarize the Laplacian spectrum by a handful of eigenvalu…

• FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs

  Elijah Feldman, Dipak Meher, Carlotta Domeniconi · 19 juin 2026

  Court proceedings contain valuable evidence about human smuggling networks, but this information is often buried within unstructured, jargon-heavy legal documents. While large language models (LLMs) can support knowledge graph construction through automated information extraction, existing approache…

• Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning

  Xinyan Zhu, Yaoqi Liu, Yue Gao, Huadong Ma, Cheng Yang, Chuan Shi · 19 juin 2026

  Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in question answering, recommendation, and decision support. With the rapid development of large language models (LLMs), LLM-based KG reasoning frameworks have become increasingly popular by leveraging retr…

• An Information Theoretic Framework for Graph Novelty Generation via Latent Mixture Modeling

  Itsuki Nakagawa, Kenji Yamanishi · 19 juin 2026

  We propose an information-theoretic framework for graph novelty generation, which aims to generate data that are distinct from existing patterns while preserving global structural consistency. Our approach embeds data into a latent space, models the latent distribution using finite mixture models, a…

• Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing

  Yongchao Huang, Hassan Raza · 18 juin 2026

  The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce \textbf{Gaussian Mixture Attention (GMA)}, a probabilistic attention-style sequence mixer that replaces explicit pairwise qu…

• GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging

  Chen Zhao, Huan Huang, Yixin Xie, Jiajing Huang, Weihua Zhou · 18 juin 2026

  Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that affects millions of older adults, with prevalence expected to rise significantly in the coming years. Early diagnosis, particularly during the mild cognitive impairment (MCI) stage, is critical for timely intervention. Structu…

• Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability

  Taewoon Kim, Vincent Fran\c{c}ois-Lavet, Michael Cochez · 18 juin 2026

  Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer process in a temporal knowledge-graph memory setting and cast it…

• Compact Geometric Representations of Hierarchies

  Prashant Gokhale, Piotr Indyk, Yuhao Liu, Sandeep Silwal, Tony Chang Wang, Haike Xu · 18 juin 2026

  Computing geometric representations of data is a cornerstone of modern machine learning, typically achieved by training dual encoders which map queries and documents into a shared embedding space. Recent work of You et al. [NeurIPS '25] has extended this approach to hierarchical retrieval, where rel…

• Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations

  Fernando Zhapa-Camacho, Robert Hoehndorf · 18 juin 2026

  Multi-hop logical reasoning on knowledge graphs requires faithfully mapping the logical semantics to latent space. Current geometric embedding methods show to be useful on this task by mapping entities to geometric regions and logical operations to latent transformations. While a geometric embedding…

• FORGE: Foundational Optimization Representations from Graph Embeddings

  Zohair Shafi, Serdar Kadioglu · 18 juin 2026

  Combinatorial optimization problems are ubiquitous in science and engineering. Still, learning-based approaches to accelerate combinatorial optimization often require solving a large number of difficult instances to collect training data, incurring significant computational cost. Existing learning-b…

• GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate

  Zirong Li · 18 juin 2026

  Programmability is a missing first-class interface in fixed-tensor neural networks: editing a relation, freezing a subgraph, auditing a local function, or changing the execution backend should be an operation on the neural program rather than ad-hoc parameter surgery. GrapNet studies this graph-as-n…

• Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning

  Donald Loveland, Puja Trivedi, Ari Weinstein, Edward W Huang, Danai Koutra · 18 juin 2026

  Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs). However, applying LLMs to graphs requires linearizing their structure into sequences, introducing distortion rooted in the graph bandwidth problem. While this distortion has been shown to degrade perfor…

• Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion

  Xuling Zhang, Peng Wang, Daiyan Li, Aoran Huang, Zeiwei Chen, Yongkui Yang · 18 juin 2026

  Most graph neural network (GNN) cores rely on graph convolutions, typically implemented as message passing between direct (single-hop) neighbors. In many real-world graphs, edges can be noisy or poorly defined, limiting information propagation to local neighborhoods. Existing diffusion kernels, such…

• AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network

  Bolin Shen, Ziwei Huang, Zhiguang Cao, Yushun Dong · 18 juin 2026

  The Traveling Salesman Problem (TSP) is a cornerstone of combinatorial optimization and arises in many practical scenarios. Although graph-based learning approaches have been explored for TSP, the question of how to exploit graph structure more effectively remains open. We present the Anisotropic Gr…

• GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging

  Chen Zhao, Huan Huang, Yixin Xie, Jiajing Huang, Weihua Zhou · 17 juin 2026

  Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that affects millions of older adults, with prevalence expected to rise significantly in the coming years. Early diagnosis, particularly during the mild cognitive impairment (MCI) stage, is critical for timely intervention. Structu…

• SMGFM: Spectral Multimodal Graph Pretraining for Multimodal-Attributed Graphs

  Zhengyu Wu, Xu Wang, Hongchao Qin, Xunkai Li, Guang Zeng, Rong-Hua Li, Guoren Wang · 17 juin 2026

  Multimodal-attributed graphs (MAGs) couple graph topology with node semantics from text, images, and other modalities. Traditional graph learning contextualizes node semantics by coupling topology with node features. However, this coupling design becomes troublesome in MAGs, where structure-induced …

• Domain-Validity-Gated Metamorphic Testing of Scientific ML Surrogates

  Meng Li, Xiaohua Yang, Jie Liu, Shiyu Yan · 17 juin 2026

  Scientific machine-learning (SciML) surrogates approximate expensive simulations, but exact expected outputs for arbitrary inputs are unavailable (the oracle problem). Metamorphic testing checks relations across executions, yet a candidate relation is not automatically valid: its preconditions, outp…

• Multimodal Graph Negative Learning

  Zhengyu Wu, Xu Wang, Hongchao Qin, Xunkai Li, Guang Zeng, Rong-Hua Li, Guoren Wang · 17 juin 2026

  Multimodal attributed graphs (MAGs) integrate graph topology with heterogeneous modality attributes, such as text and images, thereby enabling richer modeling of complex relational systems. However, such expressiveness also makes learning on MAGs depend on multiple semantic sources, including struct…

• Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models

  Cosimo Gregucci, Obaidah Theeb, Daniel Hernandez, Antonio Vergari, Steffen Staab · 17 juin 2026

  Knowledge graph (KG) foundation models (KGFMs) are zero-shot generalizers: trained once, they can predict links on unseen graphs without retraining. However, understanding when and how they can robustly generalize across KGs is still an open question. In this paper, we shed some light on their gener…