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 7 / 21 页

  1. ICML 2025RelGNN: Composite Message Passing for Relational Deep Learning
  2. ICML 2025Rethinking Time Encoding via Learnable Transformation Functions
  3. ICML 2025ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems
  4. ICML 2025Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation
  5. ICML 2025Scalable Sobolev IPM for Probability Measures on a Graph
  6. ICML 2025Self-supervised Adversarial Purification for Graph Neural Networks
  7. ICML 2025Signed Laplacians for Constrained Graph Clustering
  8. ICML 2025Simple Path Structural Encoding for Graph Transformers
  9. ICML 2025Stable Fair Graph Representation Learning with Lipschitz Constraint
  10. ICML 2025Supercharging Graph Transformers with Advective Diffusion
  11. ICML 2025Test-Time Graph Neural Dataset Search With Generative Projection
  12. ICML 2025TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
  13. ICML 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
  14. ICML 2025Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph
  15. ICML 2025TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks
  16. ICML 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
  17. ICML 2025Towards characterizing the value of edge embeddings in Graph Neural Networks
  18. ICML 2025Unifews: You Need Fewer Operations for Efficient Graph Neural Networks
  19. ICML 2025What Makes a Good Feedforward Computational Graph?
  20. ICML 2025WILTing Trees: Interpreting the Distance Between MPNN Embeddings
  21. ICML 2025Zero-Shot Generalization of GNNs over Distinct Attribute Domains
  22. NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
  23. NeurIPS 2025A CLT for Polynomial GNNs on Community-Based Graphs
  24. NeurIPS 2025Adjusted Count Quantification Learning on Graphs
  25. NeurIPS 2025An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph
  26. NeurIPS 2025Association-Focused Path Aggregation for Graph Fraud Detection
  27. NeurIPS 2025Bridging Theory and Practice in Link Representation with Graph Neural Networks
  28. NeurIPS 2025Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
  29. NeurIPS 2025Depth-Width Tradeoffs for Transformers on Graph Tasks
  30. NeurIPS 2025DiffLiG: Diffusion-enhanced Liquid Graph with Attention Propagation for Grid-to-Station Precipitation Correction
  31. NeurIPS 2025Effects of Dropout on Performance in Long-range Graph Learning Tasks
  32. NeurIPS 2025Enforcing convex constraints in Graph Neural Networks
  33. NeurIPS 2025Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
  34. NeurIPS 2025Explore In-Context Message Passing Operator for Graph Neural Networks in A Mean Field Game
  35. NeurIPS 2025FoGE: Fock Space inspired encoding for graph prompting
  36. NeurIPS 2025GD$^2$: Robust Graph Learning under Label Noise via Dual-View Prediction Discrepancy
  37. NeurIPS 2025Generative Graph Pattern Machine
  38. NeurIPS 2025Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
  39. NeurIPS 2025Geometry-Aware Edge Pooling for Graph Neural Networks
  40. NeurIPS 2025GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability
  41. NeurIPS 2025Graph Alignment via Birkhoff Relaxation
  42. NeurIPS 2025Graph Data Selection for Domain Adaptation: A Model-Free Approach
  43. NeurIPS 2025Graph Neural Network Based Action Ranking for Planning
  44. NeurIPS 2025Graph Persistence goes Spectral
  45. NeurIPS 2025Graph Your Own Prompt
  46. NeurIPS 2025Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
  47. NeurIPS 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
  48. NeurIPS 2025GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
  49. NeurIPS 2025GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
  50. NeurIPS 2025HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations

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