Advanced Graph Neural Networks

Derniers papiers

• Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution

  Yazheng Liu, Xi Zhang, Sihong Xie, Hui Xiong · 10 juillet 2026

  Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy. Understanding which historical events drive model predictions can enhance trustworthiness of TGNs. Existing explanation methods overlook the memory module, the cor…

• EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy

  Wenxiu Ding, Muzhi Liu, Zheng Yan, Mingjun Wang, Yifan Zhao, Qiao Liu · 10 juillet 2026

  Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level differential privacy, a common approach is to inject nois…

• Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferences

  Runyu Yu, Zhe Xue, Ang Li · 10 juillet 2026

  In recent years, with the continuous progress of science and technology, the number of scientific research achievements has increased rapidly. As an exchange platform and medium for scientific research achievements, scientific and technological academic conferences have become increasingly abundant.…

• DiPhon: Diffusion on Graphons for Scalable Graph Generation

  Sergio Rozada, Yiming Qin, Manuel Madeira, Pascal Frossard, Alejandro Ribeiro · 9 juillet 2026

  Diffusion models represent a leading paradigm for graph generation, with notable impact in domains such as molecular design. Yet, scaling these models to large graphs remains an open problem. We approach this question in the dense-graph setting through the lens of graphons, the size-agnostic limit o…

• Any-Dimensional Learning by Sampling

  Eitan Levin, Venkat Chandrasekaran · 9 juillet 2026

  Many machine learning models are defined for inputs of different sizes, such as point clouds containing different numbers of points, sequences of tokens of different lengths, and graphs on different numbers of nodes. Such models are trained on finitely-many examples of necessarily limited sizes. How…

• Stability of Flow Models for Graph Signals

  Martin Schmidt, Gonzalo Mateos · 9 juillet 2026

  Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While favorable stability properties of Graph Neural Networks (GNNs) have been well documented, it is unclear how structural errors propagate through the dyn…

• Diffusion enabled Optimal Transport distances for graph matching

  Iman Seyedi, Francesco Archetti · 9 juillet 2026

  This paper introduces Diffusion Semi-Relaxed Fused Gromov-Wasserstein (DsrFGW), a novel method for graph comparison that unifies node features and structural connectivity through optimal transport. While traditional Gromov-Wasserstein and semi-relaxed variants (srGW, srFGW) capture graph structure, …

• Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation

  Zhiheng Zhou, Mengyao Zhou, Dengyi Zhao, Xingqin Qi, Guiying Yan · 9 juillet 2026

  Hypergraph neural networks have shown powerful capability in modeling higher-order relations, yet their predictive uncertainty remains underexplored. Unlike pairwise graphs, uncertainty in hypergraphs arises not only from noisy attributes and ambiguous labels, but also from variations in node-hypere…

• InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs

  Mayank Kharbanda, Michael Cochez, Rajiv Ratn Shah, Raghava Mutharaju · 9 juillet 2026

  Logical Multi-Hop Query Answering over Knowledge Graphs (KGs) can be formulated as querying, with an implicit completeness assumption. Current works mainly focus on Existential First Order Logic (EFO) queries. These EFO queries contain conjunction, disjunction, and negation operators. Most existing …

• Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces

  Jiaqing Xie, Yuxin Wang · 9 juillet 2026

  Spectral positional encodings (PEs) for \emph{directed} graphs face two obstacles: magnetic Laplacians require an $O(n^3)$ Hermitian eigendecomposition per potential, and their complex eigenvectors are defined only up to unitary gauge, which prior work handles with basis-invariant architectures. We …

• Generative Diffusion Models of Stochastic Graph Signals

  Yi\u{g}it Berkay Uslu, Samar Hadou, Sergio Rozada, Shirin Saeedi Bidokhti, Alejandro Ribeiro · 9 juillet 2026

  Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial markets, and wireless network optimization. In these settings, the target signals are realizations of unknown conditional distributions. However, prev…

• Integrating knowledge graphs and multilingual scholarly corpora for domain-adaptive LLMs in SSH

  Adam Faci, Alessio Miaschi, Anne Combe, Pascal Cuxac, Francesca Frontini, Nicolas Larrousse, St\'ephane Pouyllau · 8 juillet 2026

  The integration of Large Language Models (LLMs) into scientific research workflows, particularly for bibliographic discovery and literature synthesis, raises significant methodological, epistemic and regulatory challenges for the Social Sciences and Humanities (SSH), especially with regard to discip…

• Parameter-Free Encoders Remain Viable for RDB Foundation Models

  Linjie Xu, David Wipf · 8 juillet 2026

  Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As the space of potential targets is vast across enterprise settings, it is preferable to avoid learning a new model from scratch each time th…

• Intuitionistic Fuzzy Graph Embedded Random Vector Functional Link with Multiview Learning

  Vrushank Ahire, Yogesh Kumar, M. A. Ganaie · 8 juillet 2026

  Random Vector Functional Link (RVFL) networks are popular due to their fast training and universal approximation capabilities. However, RVFL models face challenges in preserving geometric relationships and utilizing multiple feature views effectively. To address these limitations we propose the Intu…

• i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler

  Rakesh Podder, Wadia Ganim, Sarath Sreedharan, Indrajit Ray, Indrakshi Ray · 8 juillet 2026

  i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies. It leverages planning compilation that provides soundness and completeness guarantees to identify attack paths, ev…

• RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation

  Sambaran Bandyopadhyay, Ananth Muppidi · 8 juillet 2026

  Multi-hop Question Answering over Knowledge Graphs faces a critical challenge: traditional retrieve-then-read pipelines break differentiability, preventing the retriever from learning to bridge the semantic gap where intermediate nodes lack lexical overlap with the query. To address this, we propose…

• Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

  Shervin Khalafi, Igor Krawczuk, Sergio Rozada, Charilaos Kanatsoulis, Antonio G Marques, Alejandro Ribeiro · 8 juillet 2026

  Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures like graph transformers have recently shown promise in denoising graphs. However, our principled understanding of attention-based graph denoising remains limite…

• Industry Classification of GitHub Repositories Using the North American Industry Classification System (NAICS)

  Kevin Xu, Alexander Quispe · 8 juillet 2026

  GitHub hosts hundreds of millions of public repositories, but the platform exposes no native mapping from repositories to standardized industry sectors. This gap limits empirical work on the geography of innovation, the industrial composition of open-source production, and the diffusion of new techn…

• Signed-Graph Recommendation as Structural Consistency Maximization

  Zifan Wang, Siyu Chen, Wenzhuo Song · 8 juillet 2026

  While signed social recommendation has shown great potential by modeling both trust and distrust relations, its effectiveness is often hindered by structural noise and data sparsity. In this work, we first identify a fundamental inconsistency across the structural, propagation, and semantic layers o…

• Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy

  Jingyun Zhang, Hao Peng, Jianxin Li, Angsheng Li, Philip S. Yu · 8 juillet 2026

  Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks. Although Graph Contrastive Learning has demonstrated promising performance, existing methods often suffer from the "structural isolation" issue during mini-batch training, ma…

• Canopy: A Heterograph Foundation Model for Metabolic Engineering

  Jake Bowden, Laurence Legon, Satnam Surae · 8 juillet 2026

  Designing microbial strains that produce high-value chemicals at commercially viable titers remains a central challenge in metabolic engineering. Existing computational approaches either rely on stoichiometric constraint-based models that cannot learn from experimental data, or apply tabular machine…

• Hyperparameter Transfer in Graph Neural Networks

  Gage DeZoort, Boris Hanin · 7 juillet 2026

  The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay. Hyperparameter transfer aims to make near-optimal hyperparameter settings consistent across model scale, so that large models can be optimized by p…

• Heterogeneous Graph Condensation via Role-Aware Clustering

  Fuyan Ou, Yulin Hu, Ye Yuan · 7 juillet 2026

  Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains computationally prohibitive. Although graph condensation methods can effectively impro…

• FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training

  Yushu Cai, Qingrui Zhu, Lei Liu, Kai Sheng, Hao Chen, Xin He · 7 juillet 2026

  Temporal Graph Neural Networks (TGNNs) are widely used for learning from dynamic graphs in applications such as recommendation, social network analysis, and traffic forecasting. However, scaling TGNN training to large dynamic graphs remains challenging due to three intertwined bottlenecks: memory I/…

• TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation

  Axel TahmasebiMoradi, Lucas Schott, Martin Royer · 7 juillet 2026

  Knowledge graphs (KGs) that underpin Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts. Proper evaluation would require instrumenting all pertinent stages: extraction, graph construction, and inference,…