图神经网络论文趋势 2023–2026

主要结论

• 图神经网络论文从 2023 年的 434 篇降到 2026 年的 183 篇，热度在回落。
• NeurIPS 是发图神经网络论文最多的会议，2023–2026 年共 489 篇，占四个会议总量的 47%。
• 交叉方向里涨得最快的是数据集与基准：同时属于两个主题的论文从 2023 年的 10 篇增至 2026 年的 10 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的时间序列是 3.2 倍，图神经网络是 0.4 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部图神经网络论文

共 434 篇，第 2 / 9 页

51. ICLR 2023Fundamental Limits in Formal Verification of Message-Passing Neural Networks
52. ICLR 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networks
53. ICLR 2023GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks
54. ICLR 2023Graph Domain Adaptation via Theory-Grounded Spectral Regularization
55. ICLR 2023Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning
56. ICLR 2023Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
57. ICLR 2023Graph Neural Networks for Link Prediction with Subgraph Sketching
58. ICLR 2023GReTo: Remedying dynamic graph topology-task discordance via target homophily
59. ICLR 2023Grounding Graph Network Simulators using Physical Sensor Observations
60. ICLR 2023Latent Graph Inference using Product Manifolds
61. ICLR 2023Learnable Graph Convolutional Attention Networks
62. ICLR 2023Learnable Topological Features For Phylogenetic Inference via Graph Neural Networks
63. ICLR 2023Learning Fair Graph Representations via Automated Data Augmentations
64. ICLR 2023Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network
65. ICLR 2023Learning Hierarchical Protein Representations via Complete 3D Graph Networks
66. ICLR 2023Learning rigid dynamics with face interaction graph networks
67. ICLR 2023LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
68. ICLR 2023Limitless Stability for Graph Convolutional Networks
69. ICLR 2023Matching receptor to odorant with protein language and graph neural networks
70. ICLR 2023MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
71. ICLR 2023Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules
72. ICLR 2023NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs
73. ICLR 2023On Compositional Uncertainty Quantification for Seq2seq Graph Parsing
74. ICLR 2023On Representing Linear Programs by Graph Neural Networks
75. ICLR 2023On Representing Mixed-Integer Linear Programs by Graph Neural Networks
76. ICLR 2023Re-parameterizing Your Optimizers rather than Architectures
77. ICLR 2023Rethinking Graph Lottery Tickets: Graph Sparsity Matters
78. ICLR 2023Rethinking the Expressive Power of GNNs via Graph Biconnectivity
79. ICLR 2023REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH
80. ICLR 2023Robust Graph Dictionary Learning
81. ICLR 2023Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective
82. ICLR 2023Serving Graph Compression for Graph Neural Networks
83. ICLR 2023Specformer: Spectral Graph Neural Networks Meet Transformers
84. ICLR 2023Strategic Classification with Graph Neural Networks
85. ICLR 2023Subsampling in Large Graphs Using Ricci Curvature
86. ICLR 2023Towards Open Temporal Graph Neural Networks
87. ICLR 2023Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States
88. ICML 2023A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
89. ICML 2023A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
90. ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
91. ICML 2023A Large-Scale Study of Probabilistic Calibration in Neural Network Regression
92. ICML 2023Adaptive Smoothing Gradient Learning for Spiking Neural Networks
93. ICML 2023All in a Row: Compressed Convolution Networks for Graphs
94. ICML 2023Alternately Optimized Graph Neural Networks
95. ICML 2023Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
96. ICML 2023Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
97. ICML 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
98. ICML 2023Boosting Graph Contrastive Learning via Graph Contrastive Saliency
99. ICML 2023Certified Robust Neural Networks: Generalization and Corruption Resistance
100. ICML 2023CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling

常见问题

2023–2026 年四大会议一共有多少篇图神经网络论文？

共 1,038 篇，按年份分别是 2023 年 434 篇、2024 年 208 篇、2025 年 213 篇、2026 年 183 篇。

NeurIPS 2026 有多少篇图神经网络论文？

NeurIPS 2026 有 74 篇图神经网络论文，上一届是 75 篇。

ICLR 2026 有多少篇图神经网络论文？

ICLR 2026 有 28 篇图神经网络论文，上一届是 45 篇。

ICML 2026 有多少篇图神经网络论文？

ICML 2026 有 68 篇图神经网络论文，上一届是 81 篇。

CVPR 2026 有多少篇图神经网络论文？

CVPR 2026 有 13 篇图神经网络论文，上一届是 12 篇。

哪个会议的图神经网络论文最多？

NeurIPS，2023–2026 年共 489 篇。