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 313 篇，第 5 / 7 页

  1. ICML 2024Position: Graph Foundation Models Are Already Here
  2. ICML 2024Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
  3. ICML 2024Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
  4. ICML 2024Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE
  5. ICML 2024Quantum Positional Encodings for Graph Neural Networks
  6. ICML 2024Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
  7. ICML 2024Robust Graph Matching when Nodes are Corrupt
  8. ICML 2024S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning
  9. ICML 2024Sign Rank Limitations for Inner Product Graph Decoders
  10. ICML 2024SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
  11. ICML 2024Stay on Topic with Classifier-Free Guidance
  12. ICML 2024Structure Your Data: Towards Semantic Graph Counterfactuals
  13. ICML 2024Surprisingly Strong Performance Prediction with Neural Graph Features
  14. ICML 2024The Expressive Power of Path-Based Graph Neural Networks
  15. ICML 2024Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
  16. ICML 2024Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
  17. ICML 2024Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
  18. ICML 2023A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
  19. ICML 2023A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
  20. ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
  21. ICML 2023A Large-Scale Study of Probabilistic Calibration in Neural Network Regression
  22. ICML 2023Adaptive Smoothing Gradient Learning for Spiking Neural Networks
  23. ICML 2023All in a Row: Compressed Convolution Networks for Graphs
  24. ICML 2023Alternately Optimized Graph Neural Networks
  25. ICML 2023Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
  26. ICML 2023Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
  27. ICML 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
  28. ICML 2023Boosting Graph Contrastive Learning via Graph Contrastive Saliency
  29. ICML 2023Certified Robust Neural Networks: Generalization and Corruption Resistance
  30. ICML 2023CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling
  31. ICML 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
  32. ICML 2023Conditional Graph Information Bottleneck for Molecular Relational Learning
  33. ICML 2023Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping
  34. ICML 2023Conformal Prediction Sets for Graph Neural Networks
  35. ICML 2023Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
  36. ICML 2023Disentangled Multiplex Graph Representation Learning
  37. ICML 2023Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
  38. ICML 2023Does a Neural Network Really Encode Symbolic Concepts?
  39. ICML 2023ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines
  40. ICML 2023Effective Neural Topic Modeling with Embedding Clustering Regularization
  41. ICML 2023Efficient Graph Field Integrators Meet Point Clouds
  42. ICML 2023Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network
  43. ICML 2023Efficient Parametric Approximations of Neural Network Function Space Distance
  44. ICML 2023Efficiently predicting high resolution mass spectra with graph neural networks
  45. ICML 2023Equivariant Polynomials for Graph Neural Networks
  46. ICML 2023Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks
  47. ICML 2023Expectation-Complete Graph Representations with Homomorphisms
  48. ICML 2023FAENet: Frame Averaging Equivariant GNN for Materials Modeling
  49. ICML 2023Feature Expansion for Graph Neural Networks
  50. ICML 2023Featured Graph Coarsening with Similarity Guarantees

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