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.

Recent papers

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• Spectral Braids: A Topological Descriptor for Dynamic Directed Networks
  Mehmet Emin Aktas, Esra Akbas · arXiv · Oct 27, 2026

  Eigenvalues are a workhorse of graph machine learning: spectral clustering, spectral graph neural networks, and graph kernels all summarize a network by the eigenvalues of a matrix. These eigenvalues are almost always treated as a static li…

• Graph Representation Learning via Adaptive Expectile Aggregation
  Tianyi Zhu, Wei Lan · arXiv · Oct 27, 2026

  Graph neural networks (GNNs) rely critically on neighborhood aggregation, yet conventional mean aggregation may fail to capture class-relevant distributional information, particularly in heterophilic graphs. We propose ExpectileGCN, an adap…

• Stable Prediction of Fluid–Rigid Body Interaction Simulation Using Physics-Guided Graph Neural Networks
  Junho Choi, Kwang-Il Kim, Seungmin Park · Journal of Korean institute... · Oct 27, 2026
• GNN-VIEW: Visual Inspection and Explanation of Graph-based Earth-System Models
  Alessandro Lucatelli, Ferdinand Unterhuber, Katharina Krenzer, Mennatallah El-Assady et al. · arXiv · Oct 26, 2026

  Machine learning Earth-system models are becoming increasingly important, and so is their development. Graph-based models, one of the most prominent approaches, allow developers to constrain the learning process before training via graph co…

• Multi-scale graph neural network approach for phase prediction in SAT solvers
  Wenjing Chang, Changhan Wang · International Journal of Da... · Oct 25, 2026
• Conformalized graph neural network emulation of regional climate extremes: an artificial intelligence evaluation of coverage guarantees under emissions-scenario shift
  Tuhafeni Nakale, Petrus Amadhila · Zenodo (CERN European Organ... · Oct 24, 2026

  Conformal prediction offers distribution-free coverage guarantees for machine-learning emulators of climate extremes, but the guarantee is only as good as the exchangeability assumption that underwrites it. Using NASA POWER monthly reanalys…

• Hybrid IF–GNN–IF Framework for Suspected Fraud Detection in Bank Switching Transactions
  Zumam Muddin, Bambang Jokonowo, Afiyati Afiyati · Journal of Information Syst... · Oct 24, 2026

  Fraud detection in financial transactions remains a major challenge in the banking industry, particularly in bank switching systems that process high transaction volumes and involve complex interactions among transaction entities. This stud…

• Satellite-derived evapotranspiration gap-filling with spatiotemporal graph neural networks: a masked-reconstruction benchmark for irrigation-scheduling reliability across Sahelian croplands
  Nourhan Mohamed Abdel-Aziz, Mariam Fouad El-Gohary · Zenodo (CERN European Organ... · Oct 24, 2026

  Reliable evapotranspiration (ET) estimates are essential for irrigation scheduling in the Sahel, yet satellite retrievals are frequently interrupted by cloud cover and sensor gaps, leaving farmers and water managers with incomplete informat…

• scHGNN: A single-cell gene regulatory network inference method based on heuristic graph neural networks
  Tianjiao Zhang, Xiaopeng Teng, Hongfei Zhang, Zhongqian Zhao et al. · Functional & Integrative Ge... · Oct 23, 2026
• On the Token Collapse Phenomenon in Textual Graph Soft Prompting
  Andrea Giuseppe Di Francesco, Rishabh Jain, Franco Maria Nardini, Nicola Tonellotto et al. · arXiv · Oct 22, 2026

  Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relational information among entities in textual prompts. G-Retrieve…

• Enhanced Facial Micro Emotion Detection using Optimized Temporal Attention Recurrent Graph Convolutional Neural Network
  G. Akilandasowmya, K. Lakshmi Joshitha · International Journal of Pa... · Oct 22, 2026

  Micro-expressions are brief natural facial expressions that reveal concealed emotions. However, traditional facial expression recognition (FER) methods struggled due to minute expression variations, limited dataset availability, and differe…

• PI-STGNN model-driven risk assessment method for leapfrog tripping in photovoltaic power plants
  Wenjiu Xu, Jinlong Wang, Lei Wang, Jun Zhou et al. · Frontiers in Energy Research · Oct 22, 2026

  Unintended fault propagation in photovoltaic plants stems primarily from collector-line leapfrog tripping, a hazard characterized by multi-factor coupling, time-varying dynamics and hidden causal links that remain difficult to fully charact…

• Quantum-Inspired Variational Optimization of neuromorphic self-supervised heterogeneous graph transformers for multimodal Parkinson’s disease representation learning
  Tarak Hussain, Bal Virdee, Irfan Alam, Sikhinam Nagamani et al. · Discover Computing · Oct 22, 2026

  Early diagnosis of Parkinson’s disease (PD) remains challenging due to the heterogeneous nature of multimodal clinical data, limited annotated datasets, suboptimal multimodal fusion strategies, and the absence of uncertainty-aware decision-…

• A hybrid spatio-temporal deep learning framework for urban travel time prediction and intelligent routing: Integrating recurrent and graph neural networks
  Zahra Rezaei, Alireza Sharifi · Sustainable Futures · Oct 22, 2026

  Accurate short-term travel-time forecasting is important for intelligent transportation systems, but reported gains can be misleading when temporal leakage, ambiguous graph definitions, normalized error units, weak baselines, or untested ro…

• Structure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion
  Geri Skenderi · arXiv · Oct 21, 2026

  A common application of the process mining discipline is to connect observed event data with Petri nets, which are bipartite, directed graphical process models with rich formal underpinnings. Recent work learns vector representations of Pet…

• Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction
  Rafael Lopes Almeida, Ina Pöhner · arXiv · Oct 21, 2026

  Graph neural networks (GNNs) are among the standard tools for molecular property prediction, but the atom-level explanations of their predictions are hard for medicinal chemists to act on. We propose a change of input representation rather …

• Implicit Feature Reweighting for Label-Free Graph Generalization
  Tianjun Yao, Chen Xi, Xinyang Li, Lixian Zhong · arXiv · Oct 21, 2026

  Graph-level out-of-distribution (OOD) generalization is critical for deploying graph neural networks in real-world applications where distribution shifts are inevitable. Existing approaches typically require class labels during representati…

• GraphCast-Mamba: Learning Non-Markovian Corrections for Weather Forecasting
  Ilya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang, Dmitry A. Abanin · arXiv · Oct 20, 2026

  Unresolved atmospheric processes can introduce history dependence beyond the short input windows used by many weather forecasting models. We introduce GraphCast--Mamba, which augments a frozen, pretrained $1^\circ$ GraphCast backbone with a…

• Kronecker Delta Rule for Long Context Linear Attention
  Anamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer et al. · arXiv · Oct 19, 2026

  We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associati…

• WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting
  Arjun Ashok, Mihir Parmar, Palash Goyal, Bhavana Dalvi Mishra et al. · arXiv · Oct 19, 2026

  Recent time series foundation models (TSFMs) can consume covariates in-context, extending zero-shot forecasting to problems driven by external factors. This enables scenario analysis: forecasting how a target responds to events that set cov…

• Learning SOCP Solver Dynamics with Graph Neural Networks
  Adam Ghalem, Lou Salaün, Davide Rinaldi, Fragkiskos D. Malliaros · arXiv · Oct 19, 2026

  Second-order cone programs (SOCPs) are a fundamental class of convex optimization problems widely applied across engineering domains. Classical interior-point methods are robust and accurate, but their iterative nature can be costly in real…

• Trustworthy Graph Neural Architectures: Calibrating Non-Stationary Environments in Network Intrusion Detection
  Ramy Ali · Zenodo (CERN European Organ... · Oct 17, 2026
• ChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular Sheaves
  Abeer Mostafa, Zahra Ahmadi · arXiv · Oct 15, 2026

  Sheaf neural networks generalize graph neural networks by assigning each edge a learned linear restriction map that specifies how the local representations of adjacent nodes relate to one another, thereby mitigating oversmoothing. Existing …

• Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods
  Andrea D'Angelo, Francesco Gullo, Davide Mottin, Sayan Ranu et al. · arXiv · Oct 15, 2026

  Graph Unlearning (GU) aims to remove the influence of specific training data from a Graph Neural Network without retraining anew. While most methods address removal of nodes and features, Edge Unlearning (EU), aiming at forgetting edges, ha…

• Graph neural networks for transmission grid topology control: Busbar information asymmetry and heterogeneous representations
  Matthijs de Jong, Jan Viebahn, Yuliya Shapovalova · Applied Energy · Oct 15, 2026
• Hybrid Graph Neural Network Ensemble with Stacked Meta-Learning for Laboratory-Conditioned Chromatographic Retention-Time Prediction
  Shengnan Wang, Qi Zhang, Xucheng Liu, Zixuan Wang et al. · The Journal of Physical Che... · Oct 15, 2026

  Abstract Accurate prediction of chromatographic retention time (RT) is valuable for compound identification in untargeted metabolomics and forensic toxicology, yet validation must account for repeated molecular structures, chemical-space co…

• Spatial Statistics for Screening Molecular Structures
  Pranoy Ray, Surya R. Kalidindi · Small · Oct 15, 2026

  ABSTRACT The dominant paradigm in computational materials discovery relies on heavily parameterized deep architectures, including message‐passing graph and equivariant networks, that typically require large density functional theory (DFT)‐l…

• Revisiting Simple Baselines for Relational Deep Learning
  Viet The Nguyen, Vijay Prakash Dwivedi, Gunther Gust · arXiv · Oct 14, 2026

  Relational deep learning has emerged as a powerful paradigm for learning end-to-end predictive models over relational databases by representing them as temporal heterogeneous graphs. Recent advances based on graph neural networks and Transf…

• Topology-aware dynamic co-evolution for robust graph learning
  Tingting Zhang, Shuxia Lu, Mengru Wang, Bin Liu · Neural Networks · Oct 14, 2026

  Graph Neural Networks (GNNs) have achieved remarkable success in learning from graph-structured data. However, recent studies have revealed their vulnerability to adversarial attacks, where imperceptible perturbations to the graph structure…