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 96 篇，第 1 / 2 页

1. ICML 2023A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
2. ICML 2023A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
3. ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
4. ICML 2023A Large-Scale Study of Probabilistic Calibration in Neural Network Regression
5. ICML 2023Adaptive Smoothing Gradient Learning for Spiking Neural Networks
6. ICML 2023All in a Row: Compressed Convolution Networks for Graphs
7. ICML 2023Alternately Optimized Graph Neural Networks
8. ICML 2023Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
9. ICML 2023Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
10. ICML 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
11. ICML 2023Boosting Graph Contrastive Learning via Graph Contrastive Saliency
12. ICML 2023Certified Robust Neural Networks: Generalization and Corruption Resistance
13. ICML 2023CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling
14. ICML 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
15. ICML 2023Conditional Graph Information Bottleneck for Molecular Relational Learning
16. ICML 2023Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping
17. ICML 2023Conformal Prediction Sets for Graph Neural Networks
18. ICML 2023Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
19. ICML 2023Disentangled Multiplex Graph Representation Learning
20. ICML 2023Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
21. ICML 2023Does a Neural Network Really Encode Symbolic Concepts?
22. ICML 2023ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines
23. ICML 2023Effective Neural Topic Modeling with Embedding Clustering Regularization
24. ICML 2023Efficient Graph Field Integrators Meet Point Clouds
25. ICML 2023Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network
26. ICML 2023Efficient Parametric Approximations of Neural Network Function Space Distance
27. ICML 2023Efficiently predicting high resolution mass spectra with graph neural networks
28. ICML 2023Equivariant Polynomials for Graph Neural Networks
29. ICML 2023Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks
30. ICML 2023Expectation-Complete Graph Representations with Homomorphisms
31. ICML 2023FAENet: Frame Averaging Equivariant GNN for Materials Modeling
32. ICML 2023Feature Expansion for Graph Neural Networks
33. ICML 2023Featured Graph Coarsening with Similarity Guarantees
34. ICML 2023From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
35. ICML 2023Function-Space Regularization in Neural Networks: A Probabilistic Perspective
36. ICML 2023GC-Flow: A Graph-Based Flow Network for Effective Clustering
37. ICML 2023Generalizing Neural Wave Functions
38. ICML 2023Generated Graph Detection
39. ICML 2023Generative Graph Dictionary Learning
40. ICML 2023Geometric Clifford Algebra Networks
41. ICML 2023GFlowOut: Dropout with Generative Flow Networks
42. ICML 2023GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming
43. ICML 2023Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
44. ICML 2023Graph Generative Model for Benchmarking Graph Neural Networks
45. ICML 2023Graph Inductive Biases in Transformers without Message Passing
46. ICML 2023Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication
47. ICML 2023Graph Mixup with Soft Alignments
48. ICML 2023Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
49. ICML 2023Graph Neural Networks with Learnable and Optimal Polynomial Bases
50. ICML 2023Graph Neural Tangent Kernel: Convergence on Large Graphs

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。