深度学习 · graph neural networks论文趋势 2023–2026

主要结论

• 深度学习 · graph neural networks论文从 2023 年的 728 篇降到 2026 年的 326 篇，热度在回落。
• NeurIPS 是发深度学习 · graph neural networks论文最多的会议，2023–2026 年共 842 篇，占四个会议总量的 51%。
• 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 9 篇增至 2026 年的 20 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 5；同组增长最快的扩散模型是 4.1 倍，深度学习 · graph neural networks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 New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
• ICML 2026A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs
• ICLR 2026Laplacian Kernelized Bandit
• CVPR 2026Gamba Mamba-based graph convolutional network with dynamic graph topology learning
• NeurIPS 2025Depth-Width Tradeoffs for Transformers on Graph Tasks
• ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
• ICLR 2025Factor Graph-based Interpretable Neural Networks
• CVPR 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
• NeurIPS 2024[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
• ICML 2024A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
• ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
• CVPR 2024Learning Structure-from-Motion with Graph Attention Networks
• NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
• ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
• ICLR 2023Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
• CVPR 2023An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity
• NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
• ICML 2026A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
• ICLR 2026GTool: Graph Enhanced Tool Planning with Large Language Model
• CVPR 2026GSNR Graph Smooth Null-Space Representation for Inverse Problems

全部深度学习 · graph neural networks论文

共 297 篇，第 2 / 6 页

51. ICLR 2025PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph
52. ICLR 2025Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
53. ICLR 2025Precedence-Constrained Winter Value for Effective Graph Data Valuation
54. ICLR 2025Quality Measures for Dynamic Graph Generative Models
55. ICLR 2025REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring
56. ICLR 2025Recovery of Causal Graph Involving Latent Variables via Homologous Surrogates
57. ICLR 2025Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features
58. ICLR 2025Scale-Free Graph-Language Models
59. ICLR 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
60. ICLR 2025SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs
61. ICLR 2025Spectro-Riemannian Graph Neural Networks
62. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
63. ICLR 2025Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming
64. ICLR 2025Training One-Dimensional Graph Neural Networks is NP-Hard
65. ICLR 2025When Graph Neural Networks Meet Dynamic Mode Decomposition
66. ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
67. ICML 2025A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
68. ICML 2025A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
69. ICML 2025A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
70. ICML 2025A Recipe for Causal Graph Regression: Confounding Effects Revisited
71. ICML 2025Adapting Precomputed Features for Efficient Graph Condensation
72. ICML 2025Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
73. ICML 2025Adversarial Combinatorial Semi-bandits with Graph Feedback
74. ICML 2025Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
75. ICML 2025Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction
76. ICML 2025Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
77. ICML 2025AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
78. ICML 2025Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
79. ICML 2025Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
80. ICML 2025Beyond Message Passing: Neural Graph Pattern Machine
81. ICML 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
82. ICML 2025Boosting Protein Graph Representations through Static-Dynamic Fusion
83. ICML 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
84. ICML 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
85. ICML 2025Commute Graph Neural Networks
86. ICML 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
87. ICML 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
88. ICML 2025Covered Forest: Fine-grained generalization analysis of graph neural networks
89. ICML 2025CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs
90. ICML 2025CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
91. ICML 2025De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs
92. ICML 2025Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph
93. ICML 2025Directed Graph Grammars for Sequence-based Learning
94. ICML 2025Discrete Neural Algorithmic Reasoning
95. ICML 2025Disentangled Graph Spectral Domain Adaptation
96. ICML 2025Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
97. ICML 2025Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms
98. ICML 2025Do We Really Need Message Passing in Brain Network Modeling?
99. ICML 2025Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
100. ICML 2025Dynamic Similarity Graph Construction with Kernel Density Estimation

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · graph neural networks论文？

共 1,648 篇，按年份分别是 2023 年 728 篇、2024 年 297 篇、2025 年 297 篇、2026 年 326 篇。

NeurIPS 2026 有多少篇深度学习 · graph neural networks论文？

NeurIPS 2026 有 102 篇深度学习 · graph neural networks论文，上一届是 91 篇。

ICLR 2026 有多少篇深度学习 · graph neural networks论文？

ICLR 2026 有 32 篇深度学习 · graph neural networks论文，上一届是 50 篇。

ICML 2026 有多少篇深度学习 · graph neural networks论文？

ICML 2026 有 168 篇深度学习 · graph neural networks论文，上一届是 141 篇。

CVPR 2026 有多少篇深度学习 · graph neural networks论文？

CVPR 2026 有 24 篇深度学习 · graph neural networks论文，上一届是 15 篇。

哪个会议的深度学习 · graph neural networks论文最多？

NeurIPS，2023–2026 年共 842 篇。