Advanced Graph Neural Networks

Derniers papiers

• Benchmarking Sheaf Neural Networks for Inductive Tasks

  Stefano Fiorini, Edoardo Coppola, Pietro Li\`o · 4 août 2026

  Sheaf Neural Networks (SNNs) generalize message passing by replacing scalar edge weights of standard Graph Neural Networks (GNNs) with learnable, edge-dependent restriction maps between node stalks. Despite their strong theoretical foundations and promising transductive results, SNNs have been evalu…

• Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning

  Xin Liu, Xiyuan Chen, Chenglong Wu, Xuan Zong, Jun Zhou, Dawei Cheng · 4 août 2026

  Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems. Accurately identifying credit fraud among billions of users is critical for minimizing financial losses and safeguarding the sustainability of inclusive financia…

• Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity

  Yinlin Zhu, Di Wu, Yi Zhang, Xunkai Li, Wang Luo, Wei-Jin Huang, Miao Hu, Guocong Quan · 4 août 2026

  Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains. Federated multimodal graph learning (FMGL) extends federated graph learning (FGL) to MAGs, ena…

• Nonlinear Laplacians Improve Signed-Directed Graph Learning

  Ali Parviz, Yuichi Yoshida · 4 août 2026

  While signed-directed graphs have been studied using linear Laplacians in the design of graph neural networks, relatively little research has focused on developing non-linear Laplacian operators for such networks. We introduce a non-linear Laplacian operator specific to signed and directed networks …

• Agentic Graph Token Reasoning

  Zhuoyi Peng, Yi Yang · 4 août 2026

  Graphs model relational data throughout science and industry, from citation networks to product co-purchase graphs. Because the nodes of many such graphs carry rich text, a growing line of work applies large language models (LLMs) to graph analysis. The most graph-native of these methods use graph t…

• HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning

  Ruichen Xu, Jingxiang Qu, Wenhan Gao, Jiaxing Zhang, Linsey Pang, Ravid Shwartz-Ziv, Yann LeCun, Yuefan Deng · 4 août 2026

  Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architectures (JEPAs) avoid explicit negative-pair construction and raw-input reconstruction by predicting masked targets directly in latent space. However, exi…

• CoRe-GNN: Multilevel Message passing on Coarsened graphs

  Antonin Joly, Nicolas Keriven, Aline Roumy · 4 août 2026

  Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers. We show that several existing scalable approaches can be written as structured modifications of the GNN propagation matrix, providing a unified perspective that exposes …

• CountTRuCoLa: Rule Learning for Interpretable Temporal Knowledge Graph Forecasting

  Julia Gastinger, Christian Meilicke, Heiner Stuckenschmidt · 4 août 2026

  We address the task of temporal knowledge graph forecasting with an inherently interpretable method based on symbolic rules. Motivated by recent work proposing a strong baseline based on recurrent facts, our approach learns four simple rule types, including temporal rules with confidence functions t…

• Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification

  V. S. Usatyuk, D. A. Sapozhnikov, S. I. Egorov · 4 août 2026

  We propose Kohn-Sham Spectral Embedding (KSSE), an energy-based model replacing the dense classifier of convolutional neural networks with a sparse-graph spectral embedding evaluated at the Nishimori temperature of an associated Random-Bond Ising Model (RBIM). Mapping pre-trained features onto quasi…

• Differentiable Lifting for Topological Neural Networks

  Jorge Luiz Franco, Gabriel Duarte, Alexander Nikitin, Moacir Ponti, Diego Mesquita, Amauri H. Souza · 4 août 2026

  Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.g., cycles and cliques) to boost the expressive power of message-passing neural networks. In turn, however, these structures are typically identified a priori through an unsupervised graph lifting operation. Notw…

• Fairness in Augmented Graph Learning: A Survey

  Renqiang Luo, Huafei Huang, Ziqi Xu, Xikun Zhang, Enyan Dai, Bo Yang, Feng Xia · 4 août 2026

  Graph learning has evolved into Augmented Graph Learning (AGL) by integrating specialized machine learning (ML) techniques. Examples include federated learning, graph transformers, and graph condensation. While enhancing model utility, AGL introduces unique intersectional fairness challenges that tr…

• Cross-Resolution Semantic Learning for Graph Domain Adaptation

  Yingxu Wang, Haoze Huang, Zhongkai Zheng, Shangsong Liang · 3 août 2026

  Graph Domain Adaptation (GDA) transfers predictive knowledge from labeled source graphs to unlabeled target graphs under distribution shift. Existing methods align representations or regularize graph structures, but do not explicitly model how class-discriminative knowledge learned at different sour…

• Multi-Granularity Position Embedding of Graphs via Granular-Ball for Link Prediction

  Sen Zhao, Cheng Liu, Shuyin Xia, Zhiyuan Liu, Yi Liu, Yi Wang, Wei Wang · 3 août 2026

  Link prediction aims to identify potential or future connections within a given graph structure. Position information is essential for link prediction, as it distinguishes homogeneous nodes through their relative relationships, facilitating the accurate capture of structural patterns and implicit co…

• Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models

  Yi Wang, Jitao Zhao, Di Jin, Dongxiao He · 3 août 2026

  Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for enabling knowledge transfer across diverse domains. Unlike traditional graph learning methods that are typically designed for in-domain settings, GFMs aim to learn transferable knowledge that can generalize to unseen gr…

• AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control

  Jingbo Cui, Jitao Zhao, Di Jin, Dongxiao He · 30 juillet 2026

  Graph Foundation Models (GFMs) aim to learn transferable knowledge from multi-domain graphs and adapt to unseen scenarios. As a fundamental source of relational semantics in graphs, the transferability of topological patterns has long been central to GFM research. However, local structural patterns …

• ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions

  Yule Li, Yifeng Lu, Zhen Wang, Zhewei Wei, Yaliang Li, Bolin Ding · 30 juillet 2026

  In recent years, graph neural networks (GNN) have achieved unprecedented successes in node classification tasks. Although GNNs inherently encode specific inductive biases (e.g., acting as low-pass or high-pass filters), most existing methods implicitly assume conditional independence among node labe…

• No Data Is Not No Risk: Visibility Aware Graph-Based Inference of Business Conduct Risk

  Tsuyoshi Iwata, Johannes Laurmaa, Ryohei Hisano · 30 juillet 2026

  The monitoring of business conduct risk is hindered by sparse, uneven, and visibility-biased data. Prior studies show that business conduct risk information and media coverage propagate through supply chain, peer, and corporate structure networks, yet incident records remain incomplete for many firm…

• Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

  Keith G. Mills, Aedan J. DeFrates, Joong Ho Kim · 30 juillet 2026

  Graph Neural Networks (GNN) facilitate effective prediction on graph data such as molecules, media networks and neural network blueprints. GNNs facilitate prediction through message passing techniques which define how information flows from a node to its neighbors. Due to the ubiquity of the graph d…

• Learned, Relied Upon, or Necessary? Separating Checkpoint Dependence from Task-Level Value in Sheaf GNNs

  Yi Liu · 29 juillet 2026

  Learned restriction maps in sheaf graph neural networks are often treated as proof that the model has discovered useful edge geometry. That conclusion does not follow from parameter movement or from a post-hoc ablation: both can show how one checkpoint is organized while leaving open whether learned…

• CondPSE: A Polynomial-Filtered Structural Encoder with Conditional Modulation for Graphs

  Woohyun Lee, Hogun Park · 29 juillet 2026

  Message-passing graph neural networks are bounded by the 1-WL test and can miss topological structure that distinguishes non-isomorphic graphs. Positional and structural encodings (PSE) inject such topology-derived signals, and learned PSE encoders such as GPSE pretrain a single encoder to produce t…

• HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks

  Phan Binh Nguyen Lam, Nguyen Thai Anh · 29 juillet 2026

  Conformal prediction (CP) provides distribution-free uncertainty quantification, and its extension to graphs is an active research direction. Diffused Adaptive Prediction Sets (DAPS) is a widely used graph-aware diffusion baseline, propagating Adaptive Prediction Sets (APS) non-conformity scores alo…

• CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer

  Ankang Yang, Jitao Zhao, Di Jin, Yuxiao Huang, Dongxiao He · 29 juillet 2026

  Graph foundation models (GFMs) have emerged as a promising paradigm for transferring knowledge across graph domains and tasks. Real-world graphs associate nodes with text, images, and other modalities, making multimodal graphs essential for representing complex entities and relations. Moreover, coll…

• What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation

  Minwoo Yu, Young-guk Ha · 28 juillet 2026

  High task performance does not show whether a model retains prediction-relevant structural information in its internal representation. Temporal graph models, for example, can achieve high future-link AUC while basic graph statistics remain difficult to recover from the same representation. We identi…

• Does Graph Compression Preserve Signal Propagation?

  Kawshik Banerjee, Khaled Mohammed Saifuddin · 28 juillet 2026

  Graph compression reduces the computational cost of graph learning, but its effect on signal propagation remains largely underexplored. Existing work evaluates compression through downstream task performance or structural preservation, neither of which directly captures how propagation dynamics chan…

• A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction

  Nouhaila Innan, M. Murali Karthick, Simeon Kandan Sonar, Vivek Chaturvedi, Muhammad Shafique · 28 juillet 2026

  Dynamic link prediction is important for modeling evolving interactions in social, communication, financial, and transportation networks. Classical temporal graph models capture changes over time, but they may struggle to represent rapidly evolving node-edge interactions in large dynamic graphs. We …