Latest Graph Neural Networks Research Papers
The newest Graph Neural Networks papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Graph Neural Networks so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Graph Neural Networks papers in your inbox — free →Recent papers
- Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNsCamille Pradel · arXiv · Sep 10, 2026
Knowledge graph foundation models such as ULTRA achieve zero-shot link prediction on unseen graphs through dedicated architectures that hard-code a transfer mechanism. In this work we move that mechanism out of the architecture and into the…
- Digital twin-informed spatiotemporal graph neural network for buffeting response prediction of a long-span bridgeS.J. Jiang, YL Xu, S. M. Li · Engineering Structures · Sep 10, 2026
- Interpretable rockburst intensity prediction using a criterion–similarity decoupled fuzzy-regularized graph convolutional networkZichen Wang, Yuxuan Liu, Shuai Xu, Peidong Su · Tunnelling and Underground ... · Sep 10, 2026
- Learning with Covariance Matrices: Principal Component Analysis Meets Learning with GraphsSaurabh Sihag, Andrea Cavallo, Elvin Isufi, Gonzalo Mateos et al. · arXiv · Sep 9, 2026
This feature article provides an overview of the theoretical foundations for coVariance neural networks (VNNs), i.e., graph neural networks (GNNs) operating on covariance matrices as graphs. Covariance matrices are ubiquitous across domains…
- Temporal heterogeneous graph neural networks for multimodal rumor detection on social mediaDong Liu, Zhiyong Wang, Rui Zhang · Multimedia Systems · Sep 6, 2026
- Edge weight concentration overcomes node degree blindness in graph based network intrusion detectionMd Hasibuzzaman · Discover Networks · Sep 6, 2026
Abstract Graph-based network intrusion detection almost universally represents attacker behavior through node-centric structural features – degree, centrality, embeddings from graph neural networks – which implicitly assume that an attacker…
- Messages Passed Along the Edges: A Interdisciplinary Mapping Review of Graph Neural Networks for Relational DataZen Revista, 10 IA · Zenodo (CERN European Organ... · Sep 3, 2026
This article presents a narrative review of Graph Neural Networks for Relational Data in the context of Artificial Intelligence. The literature on this topic has expanded substantially over recent decades, yet it remains fragmented across s…
- Messages Passed Along the Edges: A Interdisciplinary Mapping Review of Graph Neural Networks for Relational DataZen Revista, 10 IA · Zenodo (CERN European Organ... · Sep 3, 2026
This article presents a narrative review of Graph Neural Networks for Relational Data in the context of Artificial Intelligence. The literature on this topic has expanded substantially over recent decades, yet it remains fragmented across s…
- AdaH-Chain: Deterministic capacity-aware GNNs sharding in heterogeneous blockchainsZiyao Wang, Yongjiao Sun, Hengtai Zhao, Yishu Wang et al. · Tsinghua Science & Technology · Sep 3, 2026
Abstract Modern blockchain sharding protocols increasingly deploy Graph Neural Networks (GNNs) to optimize state partitioning. However, executing these learning heuristics across heterogeneous networks introduces two funda-mental challenges…
- LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style UpdatesDmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026
Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…
- Edge-Girth as a Structural Edge Feature for Graph Neural NetworksLilian Marey, Charlotte Laclau · arXiv · Sep 1, 2026
Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot tell apart receive identical representations, however deep or …
- Graph Neural Networks for Spatio-Temporal Intrusion DetectionSafa Mohamed Safa Mostafa · Zenodo (CERN European Organ... · Aug 30, 2026
- Graph Neural Networks for Spatio-Temporal Intrusion DetectionSafa Mohamed Safa Mostafa · Zenodo (CERN European Organ... · Aug 30, 2026
- Blood Pressure Estimation Using Graph Convolutional Neural Networks with Dynamic Adjacency MatrixYoungshin Kang, Cheolsoo Park · IEIE Transactions on Smart ... · Aug 27, 2026
- Uncertainty quantification using conformal prediction for mesh-based simulationsSamira Mabtoul, Izhar Ali, Shen-Shyang Ho · Philosophical Transactions ... · Aug 27, 2026
Machine learning surrogates for computational fluid dynamics (CFD) achieve substantial speedups but lack uncertainty quantification (UQ). We develop a post hoc conformal prediction (CP) framework that wraps any trained graph neural network …
- PhononBench:A Large-Scale Phonon-Based Benchmark for Dynamical Stability in Crystal GenerationXiao-Qi Han, Ze-Feng Gao, Wen-Kao Li, Peng-Jie Guo et al. · AI for Science · Aug 26, 2026
In recent years, generative artificial intelligence has made significant advances in the design of crystalline materials, giving rise to approaches based on graph neural networks, diffusion models, and large language models. Existing evalua…
- Integrating ENSO dynamics into physics-informed Graph Neural Networks for extreme evapotranspiration prediction under climate changeKwame Adutwum Gyamfi, Eun-Sung Chung · Agricultural and Forest Met... · Aug 25, 2026
- Graph-based AI approaches for supply chain risk and fraud detectionShabnam Shahzadi, Fawaz Khaled Alarfaj · International Journal of Fi... · Aug 24, 2026
Supply Chain Risk Management (SCRM) seeks to identify, assess, and mitigate risks such as fraud, operational delays, and financial irregularities to enhance supply chain resilience. This study introduces an Adversarial Autoencoder-based Het…
- A mesh-adaptive hypergraph neural network for unsteady flow around oscillating and rotating structuresRui Gao, Zhi Cheng, Rajeev K. Jaiman · Engineering Applications of... · Aug 24, 2026
- Graph neural networks to improve geospatial estimation of equine West Nile Virus outbreaksJohn M Humphreys · Open Science Framework · Aug 23, 2026
Code and supporting materials for Leveraging recurrent graph neural networks to improve geospatial estimation of equine West Nile Virus outbreaks. This project evaluates how geographic structure, temporal dependence, environmental condition…
- Code and data for HDSTAR-GNN: A heterogeneous dynamic spatiotemporal graph neural network model for quantifying spatially cascading impacts of extreme precipitation on economic growthAnonymouse · Zenodo (CERN European Organ... · Aug 23, 2026
Extreme precipitation can generate economic losses that extend beyond directly affected locations through spatial propagation and temporal persistence, yet these cascading impacts remain difficult to quantify at fine spatial resolutions. He…
- Code and data for HDSTAR-GNN: A heterogeneous dynamic spatiotemporal graph neural network model for quantifying spatially cascading impacts of extreme precipitation on economic growthAnonymouse · Zenodo (CERN European Organ... · Aug 23, 2026
Extreme precipitation can generate economic losses that extend beyond directly affected locations through spatial propagation and temporal persistence, yet these cascading impacts remain difficult to quantify at fine spatial resolutions. He…
- A hybrid CNN–GNN approach for multi-class classification and segmentation of retinal OCT imagesAryaman Chandra, Aniket Choudhury, Prateek Sharma, Kavya Singh et al. · Biomedical Signal Processin... · Aug 22, 2026
- A quantum-inspired hybrid framework for ransomware detection using graph neural networks and support vector machinesSuneeta Satpathy, Pratik Kumar Swain · Scientific Reports · Aug 22, 2026
Ransomware detection stands as a major cybersecurity problem because attackers use obfuscation methods together with encryption and polymorphic techniques to bypass static analysis systems. While classical machine learning and deep learning…
- Recent Advances in Spectral Graph Theory for Graph Neural NetworksChitra E · International Journal of Dr... · Aug 22, 2026
....
- Film Thickness Prediction from Dichromatic Interference Images Based on Dual-Wavelength Physics-Guided Graph Neural NetworkPeng Yue, Jiaqing Wang, Zhimin Shi, Chen He et al. · Lubricants · Aug 21, 2026
Dichromatic optical interferometry provides rich optical information for lubricant film-thickness measurement. However, experimental data are typically limited to a small number of discrete operating conditions, making it difficult to learn…
- Research on the causal mechanism of prefabricated building accidents: a comprehensive framework integrating association rule mining and graph neural networkWei Liu, Baojun Liang, Yuying Xu, Xiao LUO et al. · Engineering Construction & ... · Aug 20, 2026
Purpose This study investigates the causal mechanisms underlying prefabricated building construction safety accidents (PBCSA) and aims to provide a systematic framework for identifying key risk factors and propagation pathways in complex co…
- Hierarchical dynamic spatio-temporal graph neural network for aerial group target intention predictionPeng Sun, Yongzhuang Zhang, Bin Liu, Jieyong Zhang et al. · Journal of King Saud Univer... · Aug 20, 2026
Predicting the intention of aerial group targets is central to battlefield situation awareness: the aim is to forecast, from a sequence of historical observations, how the future tactical intentions of heterogeneous formations will evolve. …
- A federated hybrid GNN-transformer framework for efficient traffic management in the Internet of VehiclesPallati Narsimhulu, Rashmi Sahay · Scientific Reports · Aug 20, 2026
Emergency healthcare transportation in the Internet of Vehicles (IoV) requires routing decisions that jointly consider traffic dynamics, wireless link reliability, medical urgency, and data privacy. Existing routing and learning-based IoV m…
- On the Fragility of Self-Improving Agents: Variance, Task Order, and UnderspecificationQinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang et al. · arXiv · Aug 18, 2026
Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods…