Graph Neural Networks papers, 2023–2026

Key findings

• Graph Neural Networks fell from 434 papers in 2023 to 183 in 2026, so interest is cooling.
• NeurIPS publishes the most Graph Neural Networks work: 489 papers from 2023 to 2026, 47% of the four-venue total.
• The fastest-growing overlap is with Datasets and Benchmarks: papers tagged with both rose from 10 in 2023 to 10 in 2026.
• Among the 5 topics under Graph and Structured Data, it ranks #4 by 2026 paper count; the fastest grower in the group, Time Series, is up 3.2x versus 0.4x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry
• ICML 2026Aitchison Embeddings for Learning Compositional Graph Representations
• ICLR 2026Certified Evaluation of Model-Level Explanations for Graph Neural Networks
• CVPR 2026Gamba Mamba-based graph convolutional network with dynamic graph topology learning
• NeurIPS 2025Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
• ICML 2025Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
• ICLR 2025Edge Prompt Tuning for Graph Neural Networks
• CVPR 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
• NeurIPS 2024[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"
• ICML 2024A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
• ICLR 2024Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
• CVPR 2024FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
• NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
• ICML 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
• ICLR 2023$\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks
• CVPR 2023Adversarially Robust Neural Architecture Search for Graph Neural Networks
• NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
• ICML 2026Any-dimensional invariant universality
• ICLR 2026Laplacian Kernelized Bandit
• CVPR 2026Global-Aware Edge Prioritization for Pose Graph Initialization

All Graph Neural Networks papers

313 papers, page 2 of 7

51. ICML 2026S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
52. ICML 2026SAGE-NAS: Synergizing LLM-Based Semantic Agent with Graph-Based Evaluator for Neural Architecture Search
53. ICML 2026SC-FAGC: Size Constrained Fast Anchor-based Graph Clustering
54. ICML 2026SFCLTA: Spectral Fusion Contrastive Learning with Topology-Adaptive Graph Augmentation
55. ICML 2026Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning
56. ICML 2026Sparse Autoencoders are Topic Models
57. ICML 2026Spike-HTR: Spiking Neural Transformer for Handwritten Text Recognition
58. ICML 2026SWING: Unlocking Implicit Graph Representations for Graph Random Features
59. ICML 2026Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
60. ICML 2026Uncertainty-Constrained Trustworthiness for Graph Learning
61. ICML 2026Understanding Truncated Positional Encodings for Graph Neural Networks
62. ICML 2026VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
63. ICML 2026Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
64. ICML 2026Watermarking Graph Neural Networks via Explanations for Ownership Protection
65. ICML 2026What Makes a Desired Graph for Relational Deep Learning?
66. ICML 2026Which Algorithms Can Graph Neural Networks Learn?
67. ICML 2026Why Are Linear RNNs More Parallelizable?
68. ICML 2026X-EviProbe: Post-hoc Parameter-Free Evidential Uncertainty Quantification for Frozen Graph Neural Networks
69. ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
70. ICML 2025A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
71. ICML 2025A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
72. ICML 2025Adapting Precomputed Features for Efficient Graph Condensation
73. ICML 2025Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
74. ICML 2025Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction
75. ICML 2025Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
76. ICML 2025AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
77. ICML 2025Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
78. ICML 2025Beyond Message Passing: Neural Graph Pattern Machine
79. ICML 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
80. ICML 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
81. ICML 2025Commute Graph Neural Networks
82. ICML 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
83. ICML 2025Covered Forest: Fine-grained generalization analysis of graph neural networks
84. ICML 2025CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
85. ICML 2025Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph
86. ICML 2025Directed Graph Grammars for Sequence-based Learning
87. ICML 2025Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
88. ICML 2025Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms
89. ICML 2025Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
90. ICML 2025Dynamic Similarity Graph Construction with Kernel Density Estimation
91. ICML 2025ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks
92. ICML 2025Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance
93. ICML 2025Enhancing Graph Invariant Learning from a Negative Inference Perspective
94. ICML 2025Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
95. ICML 2025Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
96. ICML 2025FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks
97. ICML 2025G-Adaptivity: optimised graph-based mesh relocation for finite element methods
98. ICML 2025Graph Adaptive Autoregressive Moving Average Models
99. ICML 2025GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
100. ICML 2025Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks

FAQ

How many Graph Neural Networks papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,038 in total: 434 in 2023, 208 in 2024, 213 in 2025, 183 in 2026.

How many Graph Neural Networks papers are at NeurIPS 2026?

NeurIPS 2026 has 74 Graph Neural Networks papers, versus 75 the year before.

How many Graph Neural Networks papers are at ICLR 2026?

ICLR 2026 has 28 Graph Neural Networks papers, versus 45 the year before.

How many Graph Neural Networks papers are at ICML 2026?

ICML 2026 has 68 Graph Neural Networks papers, versus 81 the year before.

How many Graph Neural Networks papers are at CVPR 2026?

CVPR 2026 has 13 Graph Neural Networks papers, versus 12 the year before.

Which conference publishes the most Graph Neural Networks papers?

NeurIPS, with 489 papers from 2023 to 2026.