Graph Neural Networks

Also known as GNN

Graph Neural Networks (GNNs) study how to learn from data whose entities and relationships form a graph, supporting tasks such as node classification, link prediction, and graph or molecular property prediction. Common approaches include message-passing networks such as GCN, GraphSAGE, and GIN, attention-based Graph Transformers, and spectral, geometric, or higher-order methods that encode richer structure. They are used on benchmarks such as Cora and ogbn-arxiv, as well as in molecular modeling, recommender systems, scientific simulation, and network control. Key open challenges include handling heterophilic graphs, preserving useful information in deep networks without oversmoothing or oversquashing, and achieving reliable generalization, robustness, and efficiency on large or shifting graphs.

Latest papers

751 papers73 papers in the last four weeks, down 13% on the four weeks before. 0.5% of all new papers.

Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing
Nov 3, 2026Alessio Borgi, Mario Severino, Luke Braithwaite +14Sheaf Neural Networks Graph Neural Networks
Department of Computer Science and Technology, University of Cambridge, Cambridge, UK · Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy · Department of Information Engineering and Computer Science, University of Trento, Trento, Italy +8
Leakage-free evaluation of residual graph convolutional networks for network intrusion detection
Nov 3, 2026Zahid IqbalNetwork Intrusion Detection Graph Neural Networks
Department of Computer Science, Faculty of Computing and Information Technology, University of Gujrat, 50700, Punjab, Pakistan
Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks
Nov 3, 2026Dawei Han, Zicheng Wang, Yaoxing Ren +3Graph Neural Networks Graph Structure Learning
National Local Joint Engineering Research Center for Precision Surgery & Regenerative Medicine, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, PR China · School of Future Technology, Xi’an Jiaotong University, Xi’an, PR China · Office of Global promotion, Division of International Cooperation and Exchanges, Xidian University +3
LENS: Reliability-Aware Stock Prediction via LLM-Extracted Priors and News-Driven Semantic Graphs
Nov 3, 2026Hao Zhou, Tiejun Ma, Luis Felipe Costa SperbStock Price Forecasting Graph Neural Networks
School of Informatics, The University of Edinburgh, Edinburgh, United Kingdom · Kingston Business School, Kingston University, London, United Kingdom
Invertible Graph Aggregation Can Increase ReLU Readout Width
Nov 1, 2026Hiroyasu Usami, Masanori Tsukamoto, Kohei HashiguchiGraph Neural Networks GNN Expressivity
Department of Computer Science, Faculty of Engineering, Chubu University, Kasugai, Japan · Department of Systemic Management for Dentistry, Kagoshima University Hospital, Kagoshima, Japan
A Surrogate Model for Variation-Aware Clock-Mesh Analysis and Design-Space Exploration using Graph Neural Networks
Nov 1, 2026Muhammad Hadir Khan, Wajid Ali, Arya Thottiparambil Manikandan +1Electronic Design Automation Neural Surrogate Modeling
University of California, Santa Cruz, USA
On Sparse Graph Limits for Neural Combinatorial Optimization
Oct 31, 2026Thien Le, Melanie WeberNeural Combinatorial Optimization Graph Neural Networks
SEAS, Harvard University, Cambridge, MA
Interpretable structural temperature scaling for calibrating graph neural networks and point-cloud segmentation
Oct 30, 2026Chenyi HuangModel Calibration Graph Neural Networks
Department of Computer Science, University College London, Gower Street, London, WC1E 6BT, United Kingdom
Accurate and Auditable ECG Classification via Visibility Graph Neural Networks
Oct 30, 2026Artur Xavier, Guilherme Henrique Gomes Evangelista, Aitazaz Khan +4Electrocardiogram Classification Interpretable Time-Series Classification
Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil. · Department of Computer Science, Rensselaer Polytechnic Institute, Troy, New York, USA. · Department of Internal Medicine, School of Medicine, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil. +1
From WSIs to Bulk, Spatial and Single-Cell Transcriptomics via Multi-Scale Graph Neural Networks
Oct 30, 2026Miguel Andrade, José Almeida, Carlos Santiago +1Spatial Gene Expression Prediction Gene Expression Prediction from Histopathology Images
Departamento de Engenharia Electrotécnica e de Computadores, Instituto Superior Técnico, Lisboa, Portugal · Champalimaud Foundation, Lisbon, Portugal
Payroll Fraud Detection in Synthetic HR/ERP Graphs: An Inductive Comparison of Rules, Path Features, and Graph Neural Networks
Oct 29, 2026Xiaobo Chen, Genliang Zhu, Ziyuan Wang +1Financial Fraud Detection Graph-Based Anomaly Detection
University of Massachusetts Amherst · Accentrust · Georgia Institute of Technology +2
Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs
Oct 29, 2026Chen Shao, Ruirui Wang, Tobias Kafer +1Text-Attributed Graph Learning Graph Neural Networks
Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany · University of Zurich, Zurich, Zurich, Switzerland · University of Michigan, Ann Arbor, Michigan, USA
Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints
Oct 28, 2026Federico Clerici, Ferran Bohigas-Daranas, Hamid Latif-Martínez +3Graph Neural Networks Power Systems
Universitat Politècnica de Catalunya · BarcelonaTech (UPC), Barcelona, Spain · Department of Mathematics, University of Padua, Padua, Italy · Centre d’Innovació Tecnològica en Convertidors Estàtics i Accionaments (CITCEA-UPC), Universitat Politècnica de Catalunya · BarcelonaTech (UPC), Barcelona, Spain +1
Predicting Cognitive Profiles from Structural MRI using Spatial Graph Representation Learning
Oct 28, 2026Taslima Ferdaus Shuva, Md. Tanvir Rahman, Risala Tasin Khan +2Graph Neural Networks Graph Representation Learning
Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, 1342, Bangladesh · Department of Computer Science and Engineering, Daffodil International University, Daffodil Smart City (DSC), Birulia, Savar, Dhaka, 1216, Bangladesh · School of Health and Rehabilitation Sciences, The University of Queensland, QLD, 4072, Australia +4
A Separation Principle for Adversarial Attacks and Defense of Graph Neural Networks
Oct 28, 2026Farid Mafi, Saber Jafarpour, Mohammad PiraniAdversarial Attacks Graph Neural Networks
University of Waterloo, Waterloo, ON, Canada · University of Colorado Boulder, Boulder, CO, USA · University of Ottawa, Ottawa, ON, Canada
Predicting Sparse Observables in Parameterized Unsteady Flows Using Coarse-Mesh Graph Neural Networks
Oct 27, 2026Brener Ramos, William R. Wolf, Tarcísio C. D. Oliveira +1PDE Surrogate Modeling Reduced-Order Modeling
School of Mechanical Engineering, University of Campinas, Campinas, São Paulo, Brazil · Department of Mechanical, Materials, and Aerospace Engineering, Illinois Institute of Technology, Chicago, Illinois, USA
GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192 $\times$ Length Extrapolation in Linear Time
Oct 27, 2026Elisabeth FinkLong-Context Modeling Sequence Modeling
Middlesex University, Department of Computer Science The Burroughs, Hendon, London NW4 4BT, UK.
GNN-Guided Network Reduction for Centralized Urban Traffic Routing
Oct 27, 2026Nikolai Antonov, Lukáš Chrpa, Andrii Nyporko +1Vehicle Routing Intelligent Transportation Systems
Czech Technical University in Prague, Czech Institute of Informatics, Robotics and Cybernetics, Jugoslávských partyzánů 1580/3, Prague, 160 00, Czech Republic · Czech Technical University in Prague, Faculty of Electrical Engineering, Technická 2, Prague, 166 27, Czech Republic
HeteGCD: Statistics-Aware Dual-Prototype Learning for Generalized Category Discovery on Heterophilous Graphs
Oct 27, 2026Xuanzhi Xi, Tongze Zhang, Zhili Qin +5Generalized Category Discovery Graph Neural Networks
University of Electronic Science and Technology of China, China
Learning atomic interactions for the thermodynamics of liquid mixtures
Oct 27, 2026Marco Hoffmann, Sebastian Schmitt, Hans Hasse +1Molecular Property Prediction Graph Neural Networks
RPTU Kaiserslautern-Landau, Kaiserslautern
Bayesian Evidence Accumulation for Graph-Based Learning in Dynamic Data-Driven Applications Systems
Oct 26, 2026Moises Ponce, Sarah Harkins Dayton, Ioannis Schizas +1Graph Classification Graph Neural Networks
University of Tennessee, Knoxville TN 37996, USA · US Army Combat Capabilities Development Command, Army Research Laboratory, Adelphi MD 20783, USA
Graph Neural Network for Wide-Area 6DoF Ambisonic Rendering
Oct 26, 2026Gioele Greco, Filippo Marri, Mirco Pezzoli +1Spatial Audio Graph Neural Networks
Dipartimento di Elettronica, Informazione e Bioingegneria - Politecnico di Milano, Milan, Italy
GNN-VIEW: Visual Inspection and Explanation of Graph-based Earth-System Models
Oct 26, 2026Alessandro Lucatelli, Ferdinand Unterhuber, Katharina Krenzer +4GNN Explainability Graph Neural Networks
ETH Zürich, Switzerland
Pricing Cross-Bank Context in Federated Anti-Money Laundering
Oct 26, 2026Lidia Losavio, Dario Fenoglio, Martin Gjoreski +1Cross-Silo Federated Learning Anti-Money Laundering Detection
Università della Svizzera italiana (USI), Lugano, Switzerland
A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access
Oct 26, 2026Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude +2Graph Neural Networks Electricity Load Forecasting
CB · LMO
MINT: Mitigating Structural Inconsistency via Attentive Message Passing for Financial Anomaly Detection
Oct 26, 2026Yin-Ju Wu, Bi-Cheng Yan, Berlin ChenGraph-Based Anomaly Detection Financial Fraud Detection
National Taiwan Normal University Taipei, Taiwan
Multiple Leak Localization in Water Distribution Networks through Graph Neural Networks
Oct 26, 2026Arvin Ajoodani, Sara Nazif, Pouria RamaziFault Localization Graph Neural Networks
School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran · Department of Biological Sciences and Department of Mathematics and Statistics, University of Calgary, Calgary, Canada
Spatially-Aware Self-Organizing Graph Autoencoders via Localized Hebbian Learning
Oct 25, 2026Robin Koç, Hazal Moğultay Özcan, Fatoş T. Yarman VuralGraph Autoencoders Visual Representation Learning
Computer Engineering Department, Middle East Technical University, Ankara, Türkiye
Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification
Oct 25, 2026Siqi Gu, Gaozhen Ma, Liheng Huang +4Graph Neural Networks Memory-Efficient Training
School of Physics and Electronic Engineering, Nanyang Normal University, Wolong District, Nanyang, 473061, Henan, China · School of Integrated Circuits, Huazhong University of Science and Technology, 1037 Luoyu Road, Hongshan District, Wuhan, 430074, Hubei, China · School of Architecture and Urban Planning, Huazhong University of Science and Technology, 1037 Luoyu Road, Hongshan District, Wuhan, 430074, Hubei, China +1
Learning Interaction-Aware Path Corrections from Unlabeled Trajectories: A LiDAR-Based Sim-to-Real GNN Framework for Construction Robots
Oct 25, 2026Yilong Chen, Yong K. ChoSocial Robot Navigation Robot Learning
School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, GA30332, United States

Nov 3, 2026J/K move · Enter open · S save

Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing

Alessio Borgi, Mario Severino, Luke Braithwaite, Steve Azzolin+13

Department of Computer Science and Technology, University of Cambridge, Cambridge, UK · Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy · Department of Information Engineering and Computer Science, University of Trento, Trento, Italy+8

Sheaf Neural Networks Graph Neural Networks Message Passing Neural Networks Graph Diffusion

Open paper AskPDF arXiv

Standard Graph Neural Networks (GNNs) implicitly assume that neighboring nodes share the same feature space, which contributes to oversmoothing and poor performance on heterophilic graphs. Sheaf Neural Networks (SNNs) remove this assumption by giving each node and edge its own vector space and learning restriction maps that transform features as they move between neighbors. These maps define a sheaf Laplacian that drives diffusion over the graph, but existing implementations often assemble it explicitly as a global sparse block matrix, which adds memory and computational overhead and can hinder scalability. In this paper, we introduce Sheaf-MPNN, a PyTorch Geometric library that reformulates sheaf diffusion as local incidence-wise transport and aggregation, eliminating the need to construct the global Laplacian. Sheaf-MPNN implements fifteen families of SNNs under a unified message-passing framework, each supporting both homogeneous and heterogeneous graphs, and directed and undirected settings, with diagonal, general, orthogonal, and low-rank restriction maps and attention-based predictors. We further provide a unified benchmarking suite covering node- and graph-level tasks, heterogeneous graph learning, and computational efficiency, enabling systematic and reproducible comparisons across architectures. We establish theoretical equivalence between these message-passing formulations and their original counterparts and identify the architectural mechanisms needed to preserve their propagation dynamics. This unified perspective provides a principled foundation for implementing, comparing, and extending sheaf-based architectures within standard graph learning frameworks. Source code is available at https://github.com/alessioborgi/sheaf-mpnn.