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 11 / 21 页

  1. ICML 2024Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
  2. ICML 2024Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE
  3. ICML 2024Quantum Positional Encodings for Graph Neural Networks
  4. ICML 2024Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
  5. ICML 2024Robust Graph Matching when Nodes are Corrupt
  6. ICML 2024S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning
  7. ICML 2024Sign Rank Limitations for Inner Product Graph Decoders
  8. ICML 2024SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
  9. ICML 2024Stay on Topic with Classifier-Free Guidance
  10. ICML 2024Structure Your Data: Towards Semantic Graph Counterfactuals
  11. ICML 2024Surprisingly Strong Performance Prediction with Neural Graph Features
  12. ICML 2024The Expressive Power of Path-Based Graph Neural Networks
  13. ICML 2024Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
  14. ICML 2024Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
  15. ICML 2024Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
  16. NeurIPS 2024[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"
  17. NeurIPS 2024Almost Surely Asymptotically Constant Graph Neural Networks
  18. NeurIPS 2024An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval
  19. NeurIPS 2024Analysis of Corrected Graph Convolutions
  20. NeurIPS 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learning
  21. NeurIPS 2024Are Graph Neural Networks Optimal Approximation Algorithms?
  22. NeurIPS 2024Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
  23. NeurIPS 2024Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
  24. NeurIPS 2024Boosting Graph Pooling with Persistent Homology
  25. NeurIPS 2024Can Graph Learning Improve Planning in LLM-based Agents?
  26. NeurIPS 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
  27. NeurIPS 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
  28. NeurIPS 2024Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
  29. NeurIPS 2024Deep Graph Mating
  30. NeurIPS 2024Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
  31. NeurIPS 2024Deep Homomorphism Networks
  32. NeurIPS 2024DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
  33. NeurIPS 2024DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
  34. NeurIPS 2024Distributed-Order Fractional Graph Operating Network
  35. NeurIPS 2024DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
  36. NeurIPS 2024Dynamic Rescaling for Training GNNs
  37. NeurIPS 2024EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection
  38. NeurIPS 2024Energy-based Epistemic Uncertainty for Graph Neural Networks
  39. NeurIPS 2024Enhancing Chess Reinforcement Learning with Graph Representation
  40. NeurIPS 2024Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
  41. NeurIPS 2024Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
  42. NeurIPS 2024Even Sparser Graph Transformers
  43. NeurIPS 2024Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
  44. NeurIPS 2024Faster Local Solvers for Graph Diffusion Equations
  45. NeurIPS 2024FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features
  46. NeurIPS 2024Generalizing CNNs to graphs with learnable neighborhood quantization
  47. NeurIPS 2024Geometric Trajectory Diffusion Models
  48. NeurIPS 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Models
  49. NeurIPS 2024Gradient Rewiring for Editable Graph Neural Network Training
  50. NeurIPS 2024GRANOLA: Adaptive Normalization 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