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 81 篇，第 1 / 2 页

1. ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
2. ICML 2025A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
3. ICML 2025A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
4. ICML 2025Adapting Precomputed Features for Efficient Graph Condensation
5. ICML 2025Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
6. ICML 2025Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction
7. ICML 2025Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
8. ICML 2025AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
9. ICML 2025Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
10. ICML 2025Beyond Message Passing: Neural Graph Pattern Machine
11. ICML 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
12. ICML 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
13. ICML 2025Commute Graph Neural Networks
14. ICML 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
15. ICML 2025Covered Forest: Fine-grained generalization analysis of graph neural networks
16. ICML 2025CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
17. ICML 2025Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph
18. ICML 2025Directed Graph Grammars for Sequence-based Learning
19. ICML 2025Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
20. ICML 2025Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms
21. ICML 2025Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
22. ICML 2025Dynamic Similarity Graph Construction with Kernel Density Estimation
23. ICML 2025ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks
24. ICML 2025Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance
25. ICML 2025Enhancing Graph Invariant Learning from a Negative Inference Perspective
26. ICML 2025Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
27. ICML 2025Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
28. ICML 2025FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks
29. ICML 2025G-Adaptivity: optimised graph-based mesh relocation for finite element methods
30. ICML 2025Graph Adaptive Autoregressive Moving Average Models
31. ICML 2025GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
32. ICML 2025Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks
33. ICML 2025Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering
34. ICML 2025Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series
35. ICML 2025Hierarchical Graph Tokenization for Molecule-Language Alignment
36. ICML 2025Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations
37. ICML 2025Implicit Subgraph Neural Network
38. ICML 2025Improved Approximations for Hard Graph Problems using Predictions
39. ICML 2025Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms
40. ICML 2025Improving Soft Unification with Knowledge Graph Embedding Methods
41. ICML 2025Improving the Effective Receptive Field of Message-Passing Neural Networks
42. ICML 2025iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
43. ICML 2025Instance Correlation Graph-based Naive Bayes
44. ICML 2025Learn Beneficial Noise as Graph Augmentation
45. ICML 2025Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
46. ICML 2025Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective
47. ICML 2025Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
48. ICML 2025ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive Learning
49. ICML 2025Multi-View Graph Clustering via Node-Guided Contrastive Encoding
50. ICML 2025N2GON: Neural Networks for Graph-of-Net with Position Awareness

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。