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 313 篇，第 1 / 7 页

1. ICML 2026A Unifying Relational Perspective on Expressive Lottery Tickets
2. ICML 2026Adaptive Node Feature Selection for Graph Neural Networks
3. ICML 2026Aitchison Embeddings for Learning Compositional Graph Representations
4. ICML 2026An Approximation Algorithm for Graph Label Selection
5. ICML 2026Anchor-guided Hypergraph Condensation with Dual-level Discrimination
6. ICML 2026Any-dimensional invariant universality
7. ICML 2026Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?
8. ICML 2026Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph Learning
9. ICML 2026Bipartite Graph Attention-based Clustering for Large-scale scRNA-seq Data
10. ICML 2026Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
11. ICML 2026Brain Networks Should Be Learned, Not Constructed
12. ICML 2026CAffNet: Hard Constraint-Affine Neural Networks
13. ICML 2026Capacity-Agnostic Parameter Isolation for Continual Graph Learning
14. ICML 2026CLINIC: Towards High-quality Graph Out-Of-Distribution Detection
15. ICML 2026Controlled Dynamics Attractor Transformer
16. ICML 2026Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series
17. ICML 2026Discriminative Attribute Graph Clustering Through Topology-Guided Contrastive Learning
18. ICML 2026Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models
19. ICML 2026Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch
20. ICML 2026EpiTwin: Spatiotemporal Graph Transformers for Epileptic sEEG Signal Reconstruction
21. ICML 2026Error-Driven Graph Augmentation for Mesh-Based PDE Surrogates
22. ICML 2026Explicitly Modeling Censoring Produces Superior Survival Predictors
23. ICML 2026Expressive Graph Neural Networks via Equivariant Use of Noise
24. ICML 2026FedRGL: Robust Federated Graph Learning under Label Noise
25. ICML 2026From Distribution to Geometry: Stable Graph Generalization via Invariant Barycenters
26. ICML 2026Full-Spectrum Graph Neural Networks: Expressive and Scalable
27. ICML 2026Gauge-Equivariant Graph Networks via Self-Interference Cancellation
28. ICML 2026GI-GCN: Global Interacted Graph Convolutional Networks via Dominant Sets for Graph Classification
29. ICML 2026Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
30. ICML 2026Graph is a Substrate Across Data Modalities
31. ICML 2026Graph Neural Networks Are Not Continuous Across Graph Resolutions
32. ICML 2026GraphP-FL: Personalized Federated Graph Learning via Dynamic Structure Awareness and Fisher Information Elastic Alignment
33. ICML 2026InvGNN: Learning Invertible Node Representations on Graphs
34. ICML 2026Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
35. ICML 2026L2G-NET: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations
36. ICML 2026Learning Molecular Semantic Invariant Representation with Prototype Constraint
37. ICML 2026Learning to Approximate Uniform Facility Location via Graph Neural Networks
38. ICML 2026Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
39. ICML 2026NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologies
40. ICML 2026On the Expressive Power of GNNs to Solve Linear SDPs
41. ICML 2026On the Spectral Unreachability of Brain Graph Learning
42. ICML 2026One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
43. ICML 2026OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph
44. ICML 2026Physics-informed coarsening for multigrid graph neural networks surrogates
45. ICML 2026Quantile-Free Uncertainty Quantification in Graph Neural Networks
46. ICML 2026RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
47. ICML 2026Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases
48. ICML 2026Rethinking Graph Transformers as Graph Signal Denoisers: The Role of Block-Diagonal Priors
49. ICML 2026Rethinking Parameter Sharing as Graph Coloring for Structured Compression
50. ICML 2026Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing

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。