NewEvery arXiv paper, its researchers & institutions — mapped.
the archive

#graph neural networks

82 results
cs.DB2026

Fully Inductive Cardinality Estimation

Tim Schwabe, Lukas Ketzer, Maribel Acosta

The paper introduces FICE, a graph neural network‑based estimator that can predict the cardinalities of SPARQL Basic Graph Pattern queries on knowledge graphs it has never seen bef…

#cardinality estimation#graph neural networks#knowledge graphs#sparql query optimization
cs.CR2026

Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting

Qingzhao Zhang

The paper examines realistic, targeted adversarial attacks on graph-based traffic forecasting models and proposes a physics‑informed detection‑based defense that improves robustnes…

#graph neural networks#traffic forecasting#adversarial attacks#physics-informed detection
cs.LG2026

Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization

Robert Jankowski, Pedro Almagro-Blanco, Marián Boguñá +2

The paper proposes training graph neural networks on geometrically renormalized, coarse‑grained versions of a graph and then directly applying the learned weights to the original f…

#graph neural networks#zero-shot transfer#geometric renormalization#graph coarsening
cs.LG2026

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks

Mostafa Haghir Chehreghani

The paper shows that injecting independent Gaussian noise after each step of a recurrent graph neural network creates a stochastic dynamical system that remains diverse, proving ma…

#graph neural networks#oversmoothing#stochastic perturbations#ergodicity
cs.LG2026

Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors

Neelam Akula, Surbhi Kumar, Murat Kantarcioglu +1

The paper defines a clean evaluation protocol for transferring knowledge between node classification and link prediction on the same graph, shows that transfer is directionally dep…

#graph neural networks#node classification#link prediction#transfer learning
cond-mat.mtrl-sci2026

Deep Learning for Accelerated Long-Horizon Forecasting of Multicomponent Multiphase Microstructure Evolution in High-Entropy Alloys

Hamidreza Razavi, Nele Moelans

The paper introduces a surrogate model combining autoencoders, graph convolutional networks, and LSTM to rapidly predict long‑term microstructure evolution in multicomponent high‑e…

#phase-field modeling#high-entropy alloys#graph neural networks#autoencoder
cs.LG2026

Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory

Jiannan Yang, Veronika Thost, Xiang Ling +1

The paper proposes a short-term graph memory module that uses an online graph neural surrogate to pre‑screen candidate molecules, allowing a fixed oracle budget to be spent on high…

#molecular optimization#oracle budget#graph neural networks#surrogate modeling
cs.CE2026

Data-free neural PDE solvers based on Graph Neural Networks and weak forms

Mikel M. Iparraguirre, Iciar Alfaro, David Gonzalez +1

The paper introduces a neural network that solves partial differential equations without any training data by using a graph neural network and the weak form of the equations, compu…

#graph neural networks#physics-informed neural networks#partial differential equations#weak formulation
cs.AI2026

A foundation model of numerical intelligence with cross-disciplinary generalization

Chenghan Wu, Zongmin Yu, Liu Yang

The paper introduces UNICON, a foundation model that learns predictive relations from graph‑based numerical contexts and can apply this numerical intelligence across scientific and…

#numerical intelligence#foundation models#graph neural networks#in-context learning
cs.AI2026

Dynamic Spectral Filtering for Temporal Graph Learning: Learning Evolving Propagation Operators

Yan Kong

The paper introduces Dynamic Spectral Filtering (DSF), a method that lets the graph propagation operator evolve over time using Chebyshev polynomial filters with time‑dependent coe…

#temporal graphs#graph neural networks#spectral filtering#link prediction
cs.LG2026

TopoFormer: Topology Meets Attention for Graph Learning

Md Joshem Uddin, Astrit Tola, Cuneyt Gurcan Akcora +1

The paper introduces TopoFormer, a framework that converts graph topology into ordered token sequences via a Topo-Scan module and processes them with a Transformer to obtain effici…

#graph representation learning#topological data analysis#transformers#graph neural networks
cond-mat.str-el2026

Graph Neural Network Force Fields for Spin Dynamics in Metallic Magnets

Ali Rayat, Yunhao Fan, Gia-Wei Chern

The paper presents a graph neural network framework that learns magnetic force fields from electronic calculations to efficiently simulate spin dynamics in metallic magnets, reprod…

#graph neural networks#magnetic force fields#spin dynamics#metallic magnets
cs.LG2026

Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus

Rasmus Tirsgaard, Laurits Fredsgaard, Marisa Wodrich +2

The paper proposes a semi-supervised learning approach for molecular graph data that uses an ensemble consensus objective to improve prediction accuracy, robustness, and calibratio…

#semi-supervised learning#molecular graphs#graph neural networks#ensemble methods
math.NA2026

Graph Neural Multilevel Preconditioners for Iterative Solvers

Zechen Zhang, Rui Peng Li, Yousef Saad

The paper proposes a Graph Neural Multilevel Preconditioner that integrates an algebraic multigrid hierarchy into a learned GNN framework to improve the convergence of iterative so…

#graph neural networks#preconditioning#multigrid#iterative solvers
cs.LG2026

FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning

Zekai Chen, Haodong Lu, Shihao Li +5

The paper introduces FedOGL, a framework for federated multimodal graph learning that mitigates catastrophic forgetting by preserving semantic and structural memory through client-…

#federated learning#graph neural networks#multimodal learning#continual learning
q-bio.NC2026

Stimulus-Evoked Network Dynamics in Human Cortical Organoids: From a Graph-Computational Framework to Repeated-Stimulation Depression

Esmaeil S. Nadimi, Vinay C. Gogineni, Jan-Matthias Braun +3

The paper presents a graph‑based computational approach to analyze how electrical stimuli trigger activity in human cortical organoids recorded with high‑density MEA, finding that…

#cortical organoids#network dynamics#graph neural networks#stimulus-evoked activity
cs.AI2026

DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation

Jiacheng Tao, Qingyun Sun, Haonan Yuan +2

The paper introduces DualG-MRAG, a framework that separates global reasoning and fine-grained evidence matching using macro and micro graphs to improve multimodal retrieval-augment…

#multimodal retrieval#graph neural networks#question answering#multi-hop reasoning
hep-th2026

Learning to Trace Seiberg Dualities

Jonathan J. Heckman, Shani Meynet, Alessandro Mininno +1

The paper applies machine learning, including transformers and MLPs, to identify Seiberg dualities in supersymmetric quiver gauge theories by learning quiver mutations, showing imp…

#seiberg duality#quiver gauge theory#machine learning#graph neural networks
cs.LG2026

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

Jingbo Cui, Jitao Zhao, Di Jin +1

The paper introduces AgentGFM, a graph foundation model where each node acts as an agent that autonomously decides how to propagate information using a trainable policy, enabling a…

#graph neural networks#foundation models#agent-based learning#information flow control
cs.CR2026

Guarding Organizations Against Malware Risk: A Novel Graph-Based Malware Detection Method

Yinan Gao, Jiarong Xu, Xiaohang Zhao +1

The paper introduces MalGuard, a graph‑based malware detection system that groups basic blocks into operational roles and learns expressive program‑graph representations to improve…

#malware detection#graph neural networks#program analysis#operational role identification
cs.IR2026

Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem

Sergei Makeev, Artem Matveev, Vladimir Baikalov +1

The paper compares pretrained graph neural network item embeddings with end‑to‑end trainable embeddings in transformer‑based sequential recommendation systems at Yandex, finding pr…

#item embeddings#graph neural networks#transformer recommendation#pretraining
cs.LG2026

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

Keith G. Mills, Aedan J. DeFrates, Joong Ho Kim

The paper evaluates how different graph neural network message‑passing layers perform on scalar regression tasks, finding that deep convolutional GNNs like GEN generally outperform…

#graph neural networks#message passing#regression#benchmarking
cs.LG2026

When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems

Quang Bui, Sparsh Roy, Akash Gundimeda +1

The paper studies when graph‑neural diffusion proposals improve solving continuous algebraic constraint systems, comparing learned proposals to random multi‑start baselines and ide…

#constraint solving#diffusion models#graph neural networks#continuous algebraic systems
cs.LG2026

Neural Architecture Search for Traffic Prediction: A Survey of Methods, Challenges, and Future Directions

Truong Giang Vu, Li Yang, Richard W. Pazzi

The paper surveys how neural architecture search techniques are used to automatically design deep learning models for traffic prediction, reviewing gradient‑based, evolutionary, an…

#traffic prediction#neural architecture search#graph neural networks#spatiotemporal modeling
← prev1 / 4next →