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 45 篇，第 1 / 1 页

1. ICLR 2025Biologically Plausible Brain Graph Transformer
2. ICLR 2025Bonsai: Gradient-free Graph Condensation for Node Classification
3. ICLR 2025Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing
4. ICLR 2025DUALFormer: Dual Graph Transformer
5. ICLR 2025Edge Prompt Tuning for Graph Neural Networks
6. ICLR 2025Exact Certification of (Graph) Neural Networks Against Label Poisoning
7. ICLR 2025Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
8. ICLR 2025Factor Graph-based Interpretable Neural Networks
9. ICLR 2025GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
10. ICLR 2025GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning
11. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
12. ICLR 2025Graph Neural Networks Can (Often) Count Substructures
13. ICLR 2025Graph Neural Networks Gone Hogwild
14. ICLR 2025Graph Neural Ricci Flow: Evolving Feature from a Curvature Perspective
15. ICLR 2025Graph Sparsification via Mixture of Graphs
16. ICLR 2025Graph Transformers Dream of Electric Flow
17. ICLR 2025Homomorphism Counts as Structural Encodings for Graph Learning
18. ICLR 2025Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
19. ICLR 2025IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning
20. ICLR 2025Improving Graph Neural Networks by Learning Continuous Edge Directions
21. ICLR 2025KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks
22. ICLR 2025Learning Efficient Positional Encodings with Graph Neural Networks
23. ICLR 2025Learning Equivariant Non-Local Electron Density Functionals
24. ICLR 2025Learning Graph Invariance by Harnessing Spuriosity
25. ICLR 2025Learning Graph Quantized Tokenizers
26. ICLR 2025Learning Long Range Dependencies on Graphs via Random Walks
27. ICLR 2025Learning Partial Graph Matching via Optimal Partial Transport
28. ICLR 2025Let Your Features Tell The Differences: Understanding Graph Convolution By Feature Splitting
29. ICLR 2025MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
30. ICLR 2025Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
31. ICLR 2025On the Completeness of Invariant Geometric Deep Learning Models
32. ICLR 2025On the Hölder Stability of Multiset and Graph Neural Networks
33. ICLR 2025PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems
34. ICLR 2025Precedence-Constrained Winter Value for Effective Graph Data Valuation
35. ICLR 2025Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features
36. ICLR 2025Scale-Free Graph-Language Models
37. ICLR 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
38. ICLR 2025SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs
39. ICLR 2025Spectro-Riemannian Graph Neural Networks
40. ICLR 2025Towards a Complete Logical Framework for GNN Expressiveness
41. ICLR 2025Towards Bridging Generalization and Expressivity of Graph Neural Networks
42. ICLR 2025Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming
43. ICLR 2025Valid Conformal Prediction for Dynamic GNNs
44. ICLR 2025When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
45. ICLR 2025When Graph Neural Networks Meet Dynamic Mode Decomposition

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。