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 4 / 21 页

  1. NeurIPS 2026Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
  2. NeurIPS 2026Invariant Hyperbolic Unfolding: Radial Canonicalization for Label-Free Cross-Graph Link Prediction
  3. NeurIPS 2026KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
  4. NeurIPS 2026Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
  5. NeurIPS 2026Long-Range Spatio-Temporal Graph Propagation Through Oscillations
  6. NeurIPS 2026MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
  7. NeurIPS 2026MIRAGE: Hierarchical MI-Surrogate Regulation for Graph Contrastive Learning
  8. NeurIPS 2026Multilateral Resistance-Guided Graph Message Passing for Trade Flow Prediction
  9. NeurIPS 2026Neighbor-Aware Snapshot-Based Temporal Graph Learning
  10. NeurIPS 2026Neural Networks With Dense Weights Are Not Universal Approximators
  11. NeurIPS 2026Neutral-atom quantum features as complementary structural encodings for graph learning
  12. NeurIPS 2026Normalized Architectures are Natively 4-Bit
  13. NeurIPS 2026OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
  14. NeurIPS 2026On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search
  15. NeurIPS 2026Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM
  16. NeurIPS 2026PATH: A Dual Perspective for High-quality Text-attributed Graph Learning
  17. NeurIPS 2026PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks
  18. NeurIPS 2026Pointwise Lipschitz Continuous Graph Algorithms
  19. NeurIPS 2026Practical Non-Stationary Graph Gaussian Processes
  20. NeurIPS 2026Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle
  21. NeurIPS 2026Robust Graph Diffusion Model
  22. NeurIPS 2026Robust Surrogate Modeling for Explainable Graph Neural Networks
  23. NeurIPS 2026Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
  24. NeurIPS 2026Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting
  25. NeurIPS 2026SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series Forecasting
  26. NeurIPS 2026SSDGExplainer: Structure-Semantic Dual-Guided Explainer for Graph Neural Networks
  27. NeurIPS 2026Toward in Silico Strain Evaluation: A Multimodal Surrogate for Fermentation Dynamics with Metabolic Graph Pretraining
  28. NeurIPS 2026Uncertainty-Aware Fuzzy Graph Contrastive Learning
  29. NeurIPS 2026WavCIL: Wavelet Coefficient-Domain Invariant Learning for Dynamic Graph OOD Generalization
  30. NeurIPS 2026Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
  31. NeurIPS 2026What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models
  32. NeurIPS 2026When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
  33. NeurIPS 2026When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees
  34. CVPR 2025Attribute-Missing Multi-view Graph Clustering
  35. CVPR 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
  36. CVPR 2025Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph
  37. CVPR 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
  38. CVPR 2025End-to-End HOI Reconstruction Transformer with Graph-based Encoding
  39. CVPR 2025FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity
  40. CVPR 2025GG-SSMs: Graph-Generating State Space Models
  41. CVPR 2025GLane3D: Detecting Lanes with Graph of 3D Keypoints
  42. CVPR 2025MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images
  43. CVPR 2025Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning
  44. CVPR 2025NN-Former: Rethinking Graph Structure in Neural Architecture Representation
  45. CVPR 2025Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping
  46. ICLR 2025Biologically Plausible Brain Graph Transformer
  47. ICLR 2025Bonsai: Gradient-free Graph Condensation for Node Classification
  48. ICLR 2025Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing
  49. ICLR 2025DUALFormer: Dual Graph Transformer
  50. ICLR 2025Edge Prompt Tuning for Graph Neural Networks

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