Graph Neural Networks

Also known as GNN

Follow this topic Ask about this topic

Latest papers 686

88 papers in the last four weeks, up 31% on the four weeks before. 0.5% of all new papers.

All topics

LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks
Jun 16, 2026Zhongyuan Wang, Pratyusha VemuriGraph Neural Networks Graph Representation Learning
Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation
Jun 16, 2026Marina Chagas Bulach Gapski, Vinicius Atsushi Sato Kawai, Gustavo Rosseto Leticio +3Graph Neural Networks Semi-Supervised Learning
Department of Statistics, Applied Mathematics, and Computing (DEMAC), São Paulo State University (UNESP), Av. 24 A, Rio Claro, SP, 13506-900, Brazil. · Institute of Mathematics and Computer Science (ICMC), University of São Paulo (USP), Av. Trabalhador São-carlense, 400 - Centro, São Carlos, SP, 13566-590, Brazil. · Department of Computer Science and Engineering, University of Quebec in Outaouais (UQO), 101 St-Jean Bosco, Gatineau, Quebec, J8X 3X7, Canada.
Finsler Geometry, Graph Neural Networks, and You
Jun 15, 2026T. Mitchell Roddenberry, Richard G. BaraniukGraph Neural Networks
Rice University, Houston, TX, USA
Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations
Jun 15, 2026Rodrigo S. Luna, Thiago H. N. Coelho, Luiz S. L. Neto +8Graph Neural Networks PDE Surrogate Modeling
Systems and Computer Engineering and High Performance Computing Center, NACAD - COPPE, Federal University of Rio de Janeiro · Civil Engineering and High Performance Computing Center, NACAD - COPPE, Federal University of Rio de Janeiro · Mechanical Engineering and High Performance Computing Center, NACAD - COPPE, Federal University of Rio de Janeiro +1
Model Graph Inductive Learning for Knowledge Graph Completion
Jun 15, 2026Mohommad Esmaei Khani, Mahdieh Hasheminejad, Ali Taherkhani +1Graph Neural Networks Link Prediction
Faculty of Mathematical Science Department of Computer Science, Yazd Unversity,, 100190, Iran. · Department of Mathematics, Institute for Advanced Studies in Basic Sciences (IASBS), 45137-66731, Iran. · Diagnostic and Research Institute of Human Genetics, Medizinische Universität Graz, Graz, 8010, Austria.
A Comparative Study of Graph Neural Network Layer Selection for Interaction Modelling in Driving Trajectory Prediction
Jun 12, 2026George Daoud, Mohamed El-DariebyGraph Neural Networks Multi-Agent Trajectory Prediction
Ontario Tech University, Oshawa, ON, Canada · Assiut University, Assiut, Egypt
Leptomeningeal Collateral Detection on DSA via Vessel-Graph Neural Networks
Jun 12, 2026Junyong Cao, Hakim Baazaoui, Chinmay Prabhakar +5Medical Imaging Graph Neural Networks
University of Zurich, Zurich, Switzerland · University Hospital Zurich, Zurich, Switzerland
When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More
Jun 12, 2026Zhongyuan Wang, Pratyusha VemuriGraph Neural Networks LLM Reasoning with Graphs
Curvature-Informed Potential Energy Surface for Protein-Ligand Binding Affinity Prediction
Jun 12, 2026Peng-Fei Sun, Chuan-Xian Ren, Hong YanProtein-Ligand Binding Affinity Prediction Graph Neural Networks
School of Mathematics, Sun Yat-Sen University, Guangzhou, Guangdong 510275, China · Department of Electrical Engineering, City University of Hong Kong, Hong Kong
Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs
Jun 12, 2026Mohamed Mouhajir, Limei Wang, El Houcine Bergou +3Graph Neural Networks Protein Representation Learning
College of Computing, UM6P Morocco · Independent USA
PostDeg: Placement Beats Parameterization in LayerNorm GNNs
Jun 12, 2026Yash Tomar, Aryav DasGraph Neural Networks Layer Normalization
Purdue University · Park Tudor High School
GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging
Jun 11, 2026Chen Zhao, Huan Huang, Yixin Xie +2Graph Neural Networks Test-Time Adaptation
Department of Computer Science, Kennesaw State University, Marietta, GA, 30060 · Department of Information Technology, Kennesaw State University, Marietta, GA, 30060 · School of Data Science and Analytics, Kennesaw State University, Marietta, GA, 30060 +1
SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecasting
Jun 11, 2026Jafar Bakhshaliyev, Niels LandwehrMultivariate Time Series Forecasting Graph Neural Networks
Data Science Group, University of Hildesheim, Hildesheim, Germany
Clustering Node Attributed Networks with Graph Neural Networks and Self Learning
Jun 11, 2026Rodrigo de Sapienza Luna, Daniel Ratton FigueiredoGraph Neural Networks Graph Representation Learning
Systems Engineering and Computer Science (PESC), Federal University of Rio de Janeiro (UFRJ), Technology Center, Block H, Room 319, 68511, Cidade Universitária, Rio de Janeiro, Brazil
Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter
Jun 10, 2026Riya Bisht, Dhruv AgarwalGraph Neural Networks OOD Generalization
Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data
Jun 10, 2026Arie Soeteman, Balder ten Cate, Maurice Funk +3Graph Neural Networks Relational Reasoning
ILLC, University of Amsterdam, Amsterdam, Netherlands · Leipzig University, Leipzig, Germany · ScaDS.AI Center Dresden/Leipzig, Germany +2
DroneShield-AI: A Multi-Modal Sensor Fusion Framework for Real-Time Autonomous Drone Threat Detection, Behavioral Intent Classification, and Swarm Intelligence in Contested Airspace
Jun 10, 2026Marius BayizereGraph Neural Networks Intent Classification
Independent Researcher, Kigali, Rwanda
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
Jun 10, 2026Anton Firc, Vojtěch Staněk, Zbyněk Lička +2Efficient Neural Network Inference Graph Neural Networks
Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS
Jun 10, 2026Siyuan Dai, Yang Du, Kun Zhao +6Graph Neural Networks Multimodal Graph Learning
Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA. · Department of Computer Science, University of Maryland, College Park, MD · Imaging Genetics Center, Mark & Mary Stevens Institute for Neuroimaging & Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA +2
GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs
Jun 10, 2026Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu +2LLM Evaluation Graph Neural Networks
The Hong Kong University of Science and Technology · Webank
Analog Quantum Asynchronous Event-Based Graph Neural Network
Jun 9, 2026Kristian Sotirov, Shaheen Acheche, Antonio A. Gentile +1Graph Neural Networks Quantum Neural Networks
King’s Communications, Learning and Information Processing (KCLIP) lab within the Centre for Intelligent Information Processing Systems (CIIPS) at the Department of Engineering, King’s College London, London, WC2R 2LS, UK · Pasqal SAS, 24 Av. Emile Baudot, 91120 Palaiseau, France · Institute for Intelligent Networked Systems (INSI), Northeastern University London, One Portsoken Street, London E1 8PH, United Kingdom
When Design Rules Break: Benchmark Composition Determines Whether Label Informativeness Predicts GNN Aggregator Choice
Jun 8, 2026Neha Sharma, Ritesh SharmaGraph Neural Networks Node Classification
Department of Computer Science Virginia Commonwealth University · Department of Electrical and Computer Engineering Virginia Commonwealth University
Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport
Jun 8, 2026Md Sadek Hossain Asif, Tanzila Khan, Md. Mosaddek KhanTemporal GNNs Graph Neural Networks
University of Dhaka
What Makes a Desired Graph for Relational Deep Learning?
Jun 7, 2026Yao Cheng, Siqiang LuoGraph Structure Learning Graph Neural Networks
Nanyang Technological University, College of Computing and Data Science, Singapore.
The Confidence Trap: Calibration Attacks for Graph Neural Networks
Jun 7, 2026Cuong Dang, Jiahao Zhang, Hieu Ta Quang +3Graph Neural Networks Adversarial Attacks
Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg, VA, USA · The Pennsylvania State University University Park, PA, USA · Center for AI Research VinUniversity Hanoi, Vietnam +1
GeoGNN: Time Series Geo-Localization using Two-Tower Graph Neural Networks
Jun 6, 2026Toan Tran, Waqwoya Abebe, Abhishek Potnis +4Graph Neural Networks Geospatial Representation Learning
Emory University Atlanta, GA, USA · Oak Ridge National Laboratory Oak Ridge, TN, USA · University of Southern California Los Angeles, CA, USA
Mesh Graph Neural Network Framework for Accelerating Finite Element Simulation for Arbitrary Geometries
Jun 6, 2026Josiah D. Kunz, Kamal ChoudharyNeural Surrogate Modeling Graph Neural Networks
Illinois College, Jacksonville, IL, USA · Department of Materials Science and Engineering, Whiting School of Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA
Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense
Jun 6, 2026Zhanke Zhou, Bo Han, Xuan Li +3Graph Neural Networks Privacy-Preserving ML
TMLR Group, Department of Computer Science, Hong Kong Baptist University, Kowloon Tong · Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China · Department of Computer Science, Stanford University, Stanford, CA 94305, USA +1
Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs
Jun 5, 2026Takuto Takahashi, Itsuki Nakayama, Takahiro Mitani +3Graph Neural Networks Node Classification
The University of Osaka, 1-5 Yamadaoka, Suita, Osaka, Japan
Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction
Jun 5, 2026Juergen DietrichGraph Neural Networks Knowledge Graphs
AI Solutions Berlin

Jun 16, 2026J/K move · Enter open · S save

LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks

Zhongyuan Wang, Pratyusha Vemuri

Graph Neural Networks Graph Representation Learning Text-Attributed Graph Learning Node Classification LLMs for Graph Learning

Open paper AskPDF arXiv

Adding LLM-generated node features to graph neural networks (GNNs) is widely reported to improve accuracy on standard benchmarks. We document a contrasting observation: when LLM features are introduced through pure input concatenation (rather than joint training, distillation, or prompt-conditioning), they can systematically degrade accuracy on the same homophilous benchmarks where end-to-end LLM pipelines succeed. With an MLP backbone on the Planetoid public split and bag-of-words original features, concatenating SBERT-encoded GPT-4o-mini TAPE features reduces PubMed test accuracy by -17.0 +/- 0.3 pp and Cora by -4.3 +/- 0.6 pp (CiteSeer -0.6 +/- 0.8 pp, within seed noise). The drop attenuates as we relax each condition (GCN / GCNII / GAT backbones, random splits, smaller encoders) and reverses on medium-homophily WikiCS (+4.4 pp) and ogbn-arxiv (+11.7 pp). To predict when concatenation helps versus hurts, we report a simple measure of LLM-alone discriminability, Delta_sig. Across 9 datasets Delta_sig correlates with the concatenation cost more strongly than homophily at point estimate (r^2 = 0.38 vs. 0.06; N=9, bootstrap CIs overlap). The bootstrap-best change-point is tau = 13.8 pp, and the rule "Delta_sig <= tau predicts non-positive concat cost" classifies 7/9 datasets correctly; since 60% of bootstrap samples place tau in [5, 30] pp, we treat Delta_sig as an interpretive lens rather than a precision filter. A dimension-controlled ablation on PubMed places the LLM-feature drop between same-source PCA (-2.3 pp) and same-dim Gaussian noise (-37.3 pp), ruling out dimensionality and weight-decay artifacts. Nine PubMed configurations fit a power law |Delta_concat| proportional to (sqrt(d_l/n))^1.31 with r^2 = 0.97; the low-Delta_sig, small-n corner is exactly where the headline -17 pp PubMed deficit appears.