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 8 / 21 页

  1. NeurIPS 2025Hierarchical Shortest-Path Graph Kernel Network
  2. NeurIPS 2025Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings
  3. NeurIPS 2025How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
  4. NeurIPS 2025HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling
  5. NeurIPS 2025Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
  6. NeurIPS 2025Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models
  7. NeurIPS 2025Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two Perspectives
  8. NeurIPS 2025Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
  9. NeurIPS 2025Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective
  10. NeurIPS 2025MaNGO — Adaptable Graph Network Simulators via Meta-Learning
  11. NeurIPS 2025Memorization in Graph Neural Networks
  12. NeurIPS 2025Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
  13. NeurIPS 2025NeuroH-TGL: Neuro-Heterogeneity Guided Temporal Graph Learning Strategy for Brain Disease Diagnosis
  14. NeurIPS 2025On Logic-based Self-Explainable Graph Neural Networks
  15. NeurIPS 2025On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
  16. NeurIPS 2025On topological descriptors for graph products
  17. NeurIPS 2025Optimal Graph Clustering without Edge Density Signals
  18. NeurIPS 2025Over-squashing in Spatiotemporal Graph Neural Networks
  19. NeurIPS 2025ProfiX: Improving Profile-Guided Optimization in Compilers with Graph Neural Networks
  20. NeurIPS 2025Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
  21. NeurIPS 2025Pseudo-Riemannian Graph Transformer
  22. NeurIPS 2025RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases
  23. NeurIPS 2025Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks
  24. NeurIPS 2025Relieving the Over-Aggregating Effect in Graph Transformers
  25. NeurIPS 2025Rethinking Tokenized Graph Transformers for Node Classification
  26. NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
  27. NeurIPS 2025Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
  28. NeurIPS 2025Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN
  29. NeurIPS 2025Robust Explanations of Graph Neural Networks via Graph Curvatures
  30. NeurIPS 2025Robust Graph Condensation via Classification Complexity Mitigation
  31. NeurIPS 2025Self-Assembling Graph Perceptrons
  32. NeurIPS 2025SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction
  33. NeurIPS 2025SONAR: Long-Range Graph Propagation Through Information Waves
  34. NeurIPS 2025Sound Logical Explanations for Mean Aggregation Graph Neural Networks
  35. NeurIPS 2025Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
  36. NeurIPS 2025TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
  37. NeurIPS 2025Taxonomy of reduction matrices for Graph Coarsening
  38. NeurIPS 2025The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
  39. NeurIPS 2025The quest for the GRAph Level autoEncoder (GRALE)
  40. NeurIPS 2025Towards Generalizable Retina Vessel Segmentation with Deformable Graph Priors
  41. NeurIPS 2025Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs
  42. NeurIPS 2025Towards Pre-trained Graph Condensation via Optimal Transport
  43. NeurIPS 2025Training Robust Graph Neural Networks by Modeling Noise Dependencies
  44. NeurIPS 2025Universally Invariant Learning in Equivariant GNNs
  45. NeurIPS 2025Unsupervised Federated Graph Learning
  46. NeurIPS 2025You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network
  47. CVPR 2024Adaptive Hyper-graph Aggregation for Modality-Agnostic Federated Learning
  48. CVPR 2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly
  49. CVPR 2024FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
  50. CVPR 2024GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs

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