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 68 篇，第 1 / 2 页

1. ICML 2024A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
2. ICML 2024A Near-Linear Time Approximation Algorithm for Beyond-Worst-Case Graph Clustering
3. ICML 2024An Efficient Maximal Ancestral Graph Listing Algorithm
4. ICML 2024An Empirical Study of Realized GNN Expressiveness
5. ICML 2024Class-Imbalanced Graph Learning without Class Rebalancing
6. ICML 2024Collective Certified Robustness against Graph Injection Attacks
7. ICML 2024Community-Invariant Graph Contrastive Learning
8. ICML 2024Comparing Graph Transformers via Positional Encodings
9. ICML 2024Cooperative Graph Neural Networks
10. ICML 2024Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
11. ICML 2024Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
12. ICML 2024Editing Partially Observable Networks via Graph Diffusion Models
13. ICML 2024Effective Federated Graph Matching
14. ICML 2024Empowering Graph Invariance Learning with Deep Spurious Infomax
15. ICML 2024EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
16. ICML 2024Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
17. ICML 2024Generalization Error of Graph Neural Networks in the Mean-field Regime
18. ICML 2024Generalized Sobolev Transport for Probability Measures on a Graph
19. ICML 2024Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization
20. ICML 2024Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
21. ICML 2024Graph As Point Set
22. ICML 2024Graph Automorphism Group Equivariant Neural Networks
23. ICML 2024Graph Distillation with Eigenbasis Matching
24. ICML 2024Graph External Attention Enhanced Transformer
25. ICML 2024Graph Geometry-Preserving Autoencoders
26. ICML 2024Graph Mixup on Approximate Gromov–Wasserstein Geodesics
27. ICML 2024Graph Neural Network Explanations are Fragile
28. ICML 2024Graph Neural Networks Use Graphs When They Shouldn't
29. ICML 2024Graph Neural Networks with a Distribution of Parametrized Graphs
30. ICML 2024Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification
31. ICML 2024Graph Structure Extrapolation for Out-of-Distribution Generalization
32. ICML 2024Graph-Triggered Rising Bandits
33. ICML 2024HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
34. ICML 2024Homomorphism Counts for Graph Neural Networks: All About That Basis
35. ICML 2024How Graph Neural Networks Learn: Lessons from Training Dynamics
36. ICML 2024How Interpretable Are Interpretable Graph Neural Networks?
37. ICML 2024How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
38. ICML 2024Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning
39. ICML 2024Learning Divergence Fields for Shift-Robust Graph Representations
40. ICML 2024Learning Graph Representation via Graph Entropy Maximization
41. ICML 2024Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational Autoencoders
42. ICML 2024Less is More: on the Over-Globalizing Problem in Graph Transformers
43. ICML 2024LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
44. ICML 2024Modelling Microbial Communities with Graph Neural Networks
45. ICML 2024Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
46. ICML 2024Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction
47. ICML 2024On the Expressive Power of Spectral Invariant Graph Neural Networks
48. ICML 2024On the Generalization of Equivariant Graph Neural Networks
49. ICML 2024On the Role of Edge Dependency in Graph Generative Models
50. ICML 2024PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

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。