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 213 篇，第 4 / 5 页

  1. NeurIPS 2025Explore In-Context Message Passing Operator for Graph Neural Networks in A Mean Field Game
  2. NeurIPS 2025FoGE: Fock Space inspired encoding for graph prompting
  3. NeurIPS 2025GD$^2$: Robust Graph Learning under Label Noise via Dual-View Prediction Discrepancy
  4. NeurIPS 2025Generative Graph Pattern Machine
  5. NeurIPS 2025Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
  6. NeurIPS 2025Geometry-Aware Edge Pooling for Graph Neural Networks
  7. NeurIPS 2025GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability
  8. NeurIPS 2025Graph Alignment via Birkhoff Relaxation
  9. NeurIPS 2025Graph Data Selection for Domain Adaptation: A Model-Free Approach
  10. NeurIPS 2025Graph Neural Network Based Action Ranking for Planning
  11. NeurIPS 2025Graph Persistence goes Spectral
  12. NeurIPS 2025Graph Your Own Prompt
  13. NeurIPS 2025Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
  14. NeurIPS 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
  15. NeurIPS 2025GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
  16. NeurIPS 2025GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
  17. NeurIPS 2025HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
  18. NeurIPS 2025Hierarchical Shortest-Path Graph Kernel Network
  19. NeurIPS 2025Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings
  20. NeurIPS 2025How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
  21. NeurIPS 2025HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling
  22. NeurIPS 2025Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
  23. NeurIPS 2025Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models
  24. NeurIPS 2025Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two Perspectives
  25. NeurIPS 2025Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
  26. NeurIPS 2025Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective
  27. NeurIPS 2025MaNGO — Adaptable Graph Network Simulators via Meta-Learning
  28. NeurIPS 2025Memorization in Graph Neural Networks
  29. NeurIPS 2025Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
  30. NeurIPS 2025NeuroH-TGL: Neuro-Heterogeneity Guided Temporal Graph Learning Strategy for Brain Disease Diagnosis
  31. NeurIPS 2025On Logic-based Self-Explainable Graph Neural Networks
  32. NeurIPS 2025On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
  33. NeurIPS 2025On topological descriptors for graph products
  34. NeurIPS 2025Optimal Graph Clustering without Edge Density Signals
  35. NeurIPS 2025Over-squashing in Spatiotemporal Graph Neural Networks
  36. NeurIPS 2025ProfiX: Improving Profile-Guided Optimization in Compilers with Graph Neural Networks
  37. NeurIPS 2025Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
  38. NeurIPS 2025Pseudo-Riemannian Graph Transformer
  39. NeurIPS 2025RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases
  40. NeurIPS 2025Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks
  41. NeurIPS 2025Relieving the Over-Aggregating Effect in Graph Transformers
  42. NeurIPS 2025Rethinking Tokenized Graph Transformers for Node Classification
  43. NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
  44. NeurIPS 2025Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
  45. NeurIPS 2025Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN
  46. NeurIPS 2025Robust Explanations of Graph Neural Networks via Graph Curvatures
  47. NeurIPS 2025Robust Graph Condensation via Classification Complexity Mitigation
  48. NeurIPS 2025Self-Assembling Graph Perceptrons
  49. NeurIPS 2025SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction
  50. NeurIPS 2025SONAR: Long-Range Graph Propagation Through Information Waves

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