图神经网络论文趋势 2023–2026

GNN 架构

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,038 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

图神经网络论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023251699618434
20248945686208
202575458112213
202674286813183

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

全部图神经网络论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,038 篇，第 20 / 21 页

  1. NeurIPS 2023Neural Oscillators are Universal
  2. NeurIPS 2023Neural Processes with Stability
  3. NeurIPS 2023Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
  4. NeurIPS 2023Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
  5. NeurIPS 2023NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
  6. NeurIPS 2023Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
  7. NeurIPS 2023No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning
  8. NeurIPS 2023Norm-based Generalization Bounds for Sparse Neural Networks
  9. NeurIPS 2023Normalization-Equivariant Neural Networks with Application to Image Denoising
  10. NeurIPS 2023Normalizing flow neural networks by JKO scheme
  11. NeurIPS 2023On the Ability of Graph Neural Networks to Model Interactions Between Vertices
  12. NeurIPS 2023On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
  13. NeurIPS 2023On the spectral bias of two-layer linear networks
  14. NeurIPS 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learning
  15. NeurIPS 2023Optimality of Message-Passing Architectures for Sparse Graphs
  16. NeurIPS 2023Optimization and Bayes: A Trade-off for Overparameterized Neural Networks
  17. NeurIPS 2023Optimizing over trained GNNs via symmetry breaking
  18. NeurIPS 2023Penalising the biases in norm regularisation enforces sparsity
  19. NeurIPS 2023PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis
  20. NeurIPS 2023Permutation Equivariant Neural Functionals
  21. NeurIPS 2023Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
  22. NeurIPS 2023Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily
  23. NeurIPS 2023Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantisation.
  24. NeurIPS 2023Provable Guarantees for Neural Networks via Gradient Feature Learning
  25. NeurIPS 2023Provable Training for Graph Contrastive Learning
  26. NeurIPS 2023QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
  27. NeurIPS 2023Quasi-Monte Carlo Graph Random Features
  28. NeurIPS 2023Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks
  29. NeurIPS 2023Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
  30. NeurIPS 2023Recurrent Temporal Revision Graph Networks
  31. NeurIPS 2023Red Teaming Deep Neural Networks with Feature Synthesis Tools
  32. NeurIPS 2023Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
  33. NeurIPS 2023Rethinking the Backward Propagation for Adversarial Transferability
  34. NeurIPS 2023Reversible and irreversible bracket-based dynamics for deep graph neural networks
  35. NeurIPS 2023Riemannian Laplace approximations for Bayesian neural networks
  36. NeurIPS 2023Riemannian Residual Neural Networks
  37. NeurIPS 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model
  38. NeurIPS 2023Robustness Guarantees for Adversarially Trained Neural Networks
  39. NeurIPS 2023Self-supervised Graph Neural Networks via Low-Rank Decomposition
  40. NeurIPS 2023Separable Physics-Informed Neural Networks
  41. NeurIPS 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
  42. NeurIPS 2023Sheaf Hypergraph Networks
  43. NeurIPS 2023Should Under-parameterized Student Networks Copy or Average Teacher Weights?
  44. NeurIPS 2023Simplicity Bias in 1-Hidden Layer Neural Networks
  45. NeurIPS 2023Simplifying Neural Network Training Under Class Imbalance
  46. NeurIPS 2023Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization
  47. NeurIPS 2023Spectral Evolution and Invariance in Linear-width Neural Networks
  48. NeurIPS 2023Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
  49. NeurIPS 2023Spike-driven Transformer
  50. NeurIPS 2023Spiking PointNet: Spiking Neural Networks for Point Clouds

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查图神经网络在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "graph-neural-networks-topic"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「图与结构化数据」下的其他主题