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

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

Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
Sep 23, 2025Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki +2Graph Neural Networks Reinforcement Learning
Oxford Robotics Institute, University of Oxford · Stateful Robotics
Learning Contact Dynamics through Touching: Action-conditional Graph Neural Networks for Robotic Peg Insertion
Sep 15, 2025Zongyao Yi, Joachim Hertzberg, Martin AtzmuellerGraph Neural Networks Contact-Rich Robotic Manipulation
German Research Center for Artificial Intelligence, DFKI Niedersachsen, Osnabrück, Germany · Osnabrück University, Institute of Computer Science, Osnabrück, Germany
Alternative Graph Neural Networks: Synergizing GEV Models and Deep Learning for Travel Mode Choice Modeling
Sep 8, 2025Yuqi Zhou, Zhanhong Cheng, Dingyi Zhuang +3Graph Neural Networks Discrete Choice Modeling
aDepartment of Urban and Regional Planning, University of Florida · dDepartment of Civil and Environmental Engineering, Massachusetts Institute of Technology · bCollege of Architecture, Texas A&M University +1
A Note on Graphon-Signal Analysis of Graph Neural Networks
Aug 25, 2025Levi Rauchwerger, Ron LevieGraphon Theory Graph Neural Networks
RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction
Aug 22, 2025Anahita Asadi, Leonid Popryho, Inna Partin-VaisbandNeural Surrogate Modeling Graph Neural Networks
Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL 60607 USA
Learning Latent Graph Geometry via Fixed-Point Schrödinger-Type Activation: A Theoretical Study
Jul 27, 2025Dmitry Pasechnyuk-Vilensky, Martin TakáčGraph Structure Learning Graph Neural Networks
MBZUAI, UAE
RAW-Explainer: Post-hoc Explanations of Path Reasoning Graph Neural Networks for Knowledge Graph Completion
Jun 14, 2025Ryoji Kubo, Samyam Lamichhane, Djellel DifallahGNN Explainability Graph Neural Networks
New York University Abu Dhabi, Abu Dhabi, United Arab Emirates
Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings
May 19, 2025Adrien Lagesse, Marc LelargeGraph Neural Networks Synthetic Benchmark Generation
INRIA, École Normale Supérieure - PSL, Paris, France.
Relation-Aware Graph Foundation Model
May 17, 2025Jianxiang Yu, Jiapeng Zhu, Yibo Zhao +4Graph Neural Networks Graph Representation Learning
School of Data Science and Engineering, East China Normal University · Ant Group
Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
May 16, 2025Jincheng Huang, Jie Xu, Xiaoshuang Shi +3Graph Neural Networks Uncertainty Calibration
School of Computer Science and Engineering, University of Electronic Science and Technology of China · Singapore Management University · Southeast University +1
Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks
Mar 31, 2025Fangtong Zhou, Xiaorui Liu, Ruozhou Yu +1Graph Neural Networks Learning to Optimize
Department of Computer Science, North Carolina State University, Raleigh, NC, 27606, USA · School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, 85287, USA
GenShin: Guiding Rational Liposome Design by Ranking Liposomal Protein Corona through a Docking-Pose-Free GNN
Mar 16, 2025Pingfei Zhu, Hongyi Liu, Xueyan Liu +2Graph Neural Networks Materials Science
Key Laboratory of symbolic Computation and Knowledge Engineering of ministry of education, Jilin University, Qianjin Street 2699, Changchun, Jilin Province, 130012, China · State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, Xue Yuan Road 38, Beijing 100191, China
Incorporating graph neural network into route choice model
Mar 4, 2025Yuxun Ma, Toru SeoDiscrete Choice Modeling Graph Neural Networks
Department of Civil and Environmental Engineering, Institute of Science Tokyo, 2-12-1-M6-10, Meguro, Ookayama, 152-8552, Tokyo, Japan
Towards Invariance to Node Identifiers in Graph Neural Networks
Feb 19, 2025Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schonlieb +2Graph Neural Networks Invariant Representation Learning
Blavatnik School of Computer Science, Tel-Aviv University · Meta · Department of Applied Mathematics and Theoretical Physics, University of Cambridge +3
Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation
Jan 15, 2025Geon-Woo Kim, Donghyun Kim, Jeongyoon Moon +5Efficient Neural Network Inference Graph Neural Networks
The University of Texas at Austin · Georgia Institute of Technology
MEGA: Message Passing Neural Networks for Multigraphs with EdGe Attributes
Nov 29, 2024H. Çağrı Bilgi, Kubilay AtasuGraph Neural Networks Graph Representation Learning
1Delft University of Technology
Label Ensemble Perspective for Reduced-Complexity Graph Node Classification under Label Noise
Nov 17, 2024Rui Zhao, Bin Shi, Zhiming Liang +4Graph Neural Networks Node Classification
School of Computer Science and Technology, Xi’an Jiaotong University, China · Ministry of Education Key Laboratory of Intelligent Networks and Network Security, China · Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, China +2
Graph Neural Networks for Supply Chain Management: A Framework and Real World Benchmark
Nov 13, 2024Azmine Toushik Wasi, MD Shafikul IslamSupply Chain Management Graph Neural Networks
Department of Industrial and Production Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh · Department of Mechanincal and Industrial Engineering, Louisiana State University, Baton Rounge, LA, 70803, USA
Information propagation dynamics in Deep Graph Networks
Oct 14, 2024Alessio GravinaGraph Neural Networks Graph Representation Learning
University of Pisa Department of Computer Science
Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning
Sep 9, 2024Sitao Luan, Qincheng Lu, Chenqing Hua +3Graph Neural Networks Node Classification
Mila - Quebec Artiﬁcial Intelligence Institute · 1McGill University
GREAT: A Graph Edge Attention Network for the Electric Vehicle Routing Problem with Asymmetric Costs
Aug 29, 2024Attila Lischka, Filip Rydin, Jiaming Wu +2Vehicle Routing Graph Neural Networks
Chalmers University of Technology · University of Gothenburg
Physics Inspired Neural Networks Enable Efficient Graph Coloring
Aug 2, 2024Lorenzo Colantonio, Andrea Cacioppo, Federico Scarpati +3Combinatorial Optimization Neural Combinatorial Optimization
Department of Physics, Sapienza University of Rome
SSP-GNN: Learning to Track via Bilevel Optimization
Jul 5, 2024Griffin Golias, Masa Nakura-Fan, Vitaly AblavskyGraph Neural Networks Visual Object Tracking
Applied Physics Laboratory University of Washington Seattle, WA 98105 USA · Paul G. Allen School of Computer Science University of Washington Seattle, WA 98105 USA
GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
Jun 24, 2024Shengbo Gong, Juntong Ni, Noveen Sachdeva +2Graph Neural Networks Node Classification
Emory University · Google Deepmind
GENIE: Watermarking Graph Neural Networks for Link Prediction
Jun 7, 2024Venkata Sai Pranav Bachina, Aaryan Ajay Sharma, Ankit Gangwal +1Graph Neural Networks Robust Watermarking
IIIT Hyderabad, India
The Interpretable and Effective Graph Neural Additive Networks
Jun 3, 2024Maya Bechler-Speicher, Amir Globerson, Ran Gilad-BachrachGraph Neural Networks GNN Explainability
Blavatnik School of Computer Science, Tel-Aviv University · Department of Bio-Medical Engineering, Edmond J. Safra Center for Bioinformatics, Tel-Aviv University
Graph Unitary Message Passing
Mar 17, 2024Haiquan Qiu, Quanming YaoGraph Neural Networks Message Passing Neural Networks
Department of Electrical Engineering, Tsinghua University · 2Beijing National Research Center for Information Science and Technology · 3State Key laboratory of Space Network and Communications
Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework
Mar 2, 2024Junxian Li, Bin Shi, Erfei Cui +2Graph Positional Encoding Knowledge Distillation
Xi’an Jiaotong University · Arizona State University, Tempe, USA · Tongji University, Shanghai, China
Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition
Jun 8, 2023Yuxiang Zhang, Chengguo Yuan, Xiao Wang +2Event-Based Vision Graph Neural Networks
aSchool of Computer Science and Technology, Anhui University, Hefei 230601, China.
Harnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning
Jun 3, 2023Zhichao Hou, Xitong Zhang, Wei Wang +2Graph Neural Networks Adversarial Robustness
North Carolina State University · Michigan State University · Meta +1

Sep 23, 2025J/K move · Enter open · S save

Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning

Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki, Bruno Lacerda+1

Oxford Robotics Institute, University of Oxford · Stateful Robotics

Graph Neural Networks Reinforcement Learning Neural Algorithmic Reasoning RL for Combinatorial Optimization Algorithmic Reasoning Neural Combinatorial Optimization

Open paper AskPDF arXiv

Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning. Despite its successes, important limitations remain: inability to construct valid solutions without post-processing and to reason about multiple correct ones, poor performance on combinatorial NP-hard problems, and inapplicability to problems for which strong algorithms are not yet known. To address these limitations, we reframe the problem of learning algorithm trajectories as a Markov decision process, which imposes structure on the solution construction procedure and unlocks the powerful tools of imitation and reinforcement learning (RL). We propose the GNARL framework, encompassing the methodology to translate problem formulations from NAR to RL and a learning architecture suitable for a wide range of graph-based problems. We achieve high rates of reaching correct states on several CLRS-30 problems and performance matching or exceeding much narrower NAR approaches for NP-hard problems. Remarkably, GNARL remains applicable when no expert algorithm is available, though reward-driven learning can exhibit greater variability than direct supervision.