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

A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
May 27, 2026Nicolas Tremblay, Benjamin Ricaud, Filippo Maria BianchiGraph Neural Networks Graph Classification
UiT the Arctic University of Norway · & CNRS, France · & NORCE Norwegian Research Centre
Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection
May 27, 2026Zhixing Zuo, Huilin He, Jiasheng Wu +1Graph Neural Networks Graph Representation Learning
School of Computer Science and Technology, Tongji University
From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Interaction Type Prediction An Ablation Study with Acetylsalicylic Acid Validation
May 27, 2026Juergen DietrichGraph Neural Networks Cross-Attention
Sampling Triangulations and Calabi-Yau Threefolds with Autoregressive GNNs
May 26, 2026Nate MacFaddenGraph Neural Networks Generative Modeling
Department of Physics, Cornell University, Ithaca, NY 14853 USA
Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks
May 26, 2026Lihui Liu, Mucun Sun, Caisheng WangRL Control Graph Neural Networks
Wayne State University, Detroit, MI, USA
RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
May 26, 2026Yali Fink, Ido Ben-Yair, Lars Ruthotto +1Graph Neural Networks
Institute for Interdisciplinary Computational Sciences, Faculty of Computer and Information Science, Ben-Gurion University of the Negev, Be’er Sheva, Israel · Department of Mathematics and Computer Science, Emory University, Atlanta, GA, USA.
Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks
May 25, 2026Derek Regier, Andrew Polyak, Aresh Dadlani +1Temporal GNNs Graph Neural Networks
Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
May 25, 2026Zhishuai Guo, Wenhan Wu, Chen Chen +3Graph Neural Networks Communication-Efficient Distributed Training
Department of Computer Science Northern Illinois University · Department of Computer Science University of North Carolina at Charlotte · Department of Computer Science University of Central Florida +2
Invariant-Based Weight Sharing for Message Passing
May 25, 2026Florian SeiffarthGraph Neural Networks GNN Expressivity
University of Bonn, Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany
Evaluating passing decision-making in professional football: An enhanced MPNN approach to Receiver Selection
May 25, 2026Gabriel Masella, Giuseppe Alessio D'Inverno, Max Goldsmith +1Graph Neural Networks Message Passing Neural Networks
Department of Mathematics, Informatics and Geoscience, University of Trieste, via Weiss 2, Trieste, 34128, Italy. · MathLab, International School for Advanced Studies (SISSA), Via Bonomea 265, Trieste, 34136, Italy. · Royal Belgium Football Association, Rue de Bruxelles 480, Tubize, 1480, Belgium.
ARMA-C3: A Contrastive ARMA Convolutional Framework for Unsupervised and Semi-supervised Classification
May 25, 2026VSS Tejaswi Abburi, Saurabh J. Shigwan, Nitin KumarGraph Neural Networks Unsupervised Representation Learning
Department of Computer Science and Engineering, Shiv Nadar Institute of Eminence Deemed to be University, Delhi NCR, India
PHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting
May 25, 2026Ruiwen Gu, Yahao Liu, Zhenyu Liu +2Graph Neural Networks Intelligent Transportation Systems
Shenzhen Ubiquitous Data Enabling Key Lab Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · School of Computer Science and Engineering University of Electronic Science and Technology of China, Chengdu, China
Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks
May 25, 2026Nil Ayday, Mahalakshmi Sabanayagam, Debarghya GhoshdastidarNeural Network Generalization Graph Neural Networks
Technical University of Munich, School of Computation, Information and Technology, Boltzmannstr. 3, Garching, 85748, Germany. · Australian Institute for Machine Learning, Adelaide University,2026 Adelaide, SA 5000, Australia.
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
May 24, 2026Zichao Yue, Zhiru ZhangGraph Neural Networks Graph Diffusion
School of Electrical and Computer Engineering, Cornell University, Ithaca, New York, USA.
GL-LFGNN:A Global-Local Dual-branch Causal Graph Neural Network Based on Liang-Kleeman Information Flow for EEG Emotion Recognition
May 24, 2026Ziyi Wang, Dongyang KuangGraph Neural Networks EEG Emotion Recognition
Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs
May 23, 2026Hao Yan, Xuanru Wang, Jun Yin +3Graph Neural Networks Multimodal Graph Learning
School of Computer Science and Engineering, Central South University, Changsha, China · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China · School of Information and Communication Technology, Griffith University, Brisbane, Australia
Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification
May 23, 2026Rafael Mendonça Duarte, Jean Roberto Ponciano, Lucas Pascotti ValemGraph Neural Networks Graph-Based Semi-Supervised Learning
Institute of Mathematics and Computer Science (ICMC) University of São Paulo (USP) São Carlos – SP – Brazil
Whole-Body Inverse Kinematics with Graph Diffusion
May 23, 2026Helong Huang, Kai Tan, Feng Wen +2Graph Neural Networks Inverse Kinematics
Large Model Algorithm Lab, Huawei
S $^3$ GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
May 22, 2026Dai Shi, Luke Thompson, Linhan Luo +4Graph Neural Networks Graph Representation Learning
Department of Engineering, University of Cambridge, Cambridge, UK · University of Sydney, Australia
Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
May 22, 2026Snir Hordan, Nadav Dym, Tim SeppeltGraph Neural Networks GNN Expressivity
Faculty of Mathematics Technion - Israel Institute of Technology · IT University of Copenhagen
Self-supervised Adversarial Purification for Graph Neural Networks
May 22, 2026Woohyun Lee, Hogun ParkGraph Neural Networks Adversarial Robustness
Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, South Korea.
Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
May 21, 2026Pedro C. Vieira, Pedro Ribeiro, Viacheslav BorovitskiyGraph Neural Networks Deep Ensembles
University of Edinburgh · DCC/FCUP, University of Porto
Implicit Regularization of Mini-Batch Training in Graph Neural Networks
May 21, 2026Clement Wang, Antoine Vialle, Robin Vaysse +1Graph Neural Networks Implicit Regularization
Institut Polytechnique de Paris · Mirakl
Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
May 21, 2026Yoav Kor Sade, Arvindh Arun, Rishi Puri +2Graph Neural Networks LLM Reasoning with Graphs
Tel Aviv University · Institute for AI, University of Stuttgart · NVIDIA +1
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
May 20, 2026Yi Huang, Qingyun Sun, Jia Li +2Graph Structure Learning Graph Neural Networks
SKLCCSE, School of Computer Science and Engineering, Beihang University, Beijing, China · Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China
Gaussian Sheaf Neural Networks
May 20, 2026André Ribeiro, Ana Luiza Tenório, Tiago da Silva +1Graph Neural Networks Sheaf Neural Networks
Getulio Vargas Foundation · MBZUAI
Graph Navier Stokes Networks
May 20, 2026Zexing Zhao, Guangsi Shi, Yu Gong +4Graph Neural Networks Graph Diffusion
Northwest A&F University Yangling, Shaanxi, China · Corporate Research Center, Midea Group Shanghai, China · Bosch Shanghai, China
WaveGraphNet: Physics-Consistent Guided-Wave Damage Localization through Coupled Inverse-Forward Graph Learning
May 19, 2026Vinay Sharma, Aditya Bharade, Olga FinkGraph Neural Networks Inverse Problems
EPFL, Intelligent Maintenance and Operations Systems, Lausanne, Switzerland
B-cos GNNs: Faithful Explanations through Dynamic Linearity
May 19, 2026Joschka Groß, Mohammad Shaique Solanki, Verena WolfFeature Attribution Graph Neural Networks
Saarland Informatics Campus, Saarland University · DFKI
BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics
May 19, 2026Siddharth Viswanath, Panayiotis Ketonis, Cassidy All +10Graph Neural Networks Sheaf Neural Networks
Yale University · Boise State University · University of Wisconsin–Madison

May 27, 2026J/K move · Enter open · S save

A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks

Nicolas Tremblay, Benjamin Ricaud, Filippo Maria Bianchi

UiT the Arctic University of Norway · & CNRS, France · & NORCE Norwegian Research Centre

Graph Neural Networks Graph Classification GNN Explainability

Open paper AskPDF arXiv

We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which node features and which aspects of the graph topology were leveraged for prediction. In practice, the layer's propagation matrix takes the closed-form

R = (p(L)+Q)^{-1} Q

, where

L

is the normalized graph Laplacian,

Q = diag(q_1,...,q_n)

a learnable diagonal matrix of positive node-importance scores, and

p(\cdot)

a learnable polynomial. For any input feature

x

, the layer output

Rx

is the exact minimizer of a generalized graph Tikhonov problem that trades off node-level data fidelity against a topology-driven regularization penalty. The learned pair

\{\{q_i\},p\}

constitutes a built-in explanation: large

q_i

indicates that node

i

's own features drive the prediction, while small

q_i

signals reliance on the local graph topology; the shape of

p

reveals whether homophily, heterophily, or a band-pass response is exploited. Expressivity is preserved by routing complexity through a dedicated, arbitrarily deep Q-network that produces the importance scores, while the Tikhonov layer itself remains transparent. We prove that distinct node-importance matrices yield distinct propagation operators, structurally coupling the explanation to the computation. Additionally, the Tikhonov layer provides, in a single layer, a global receptive field, mitigating both oversmoothing and oversquashing. Experiments on standard graph classification benchmarks confirm that the model matches (and sometimes outperforms) opaque baselines while producing interpretable and faithful explanations.