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 434 篇，第 7 / 9 页

  1. NeurIPS 2023Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings
  2. NeurIPS 2023Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network
  3. NeurIPS 2023Individualized Dosing Dynamics via Neural Eigen Decomposition
  4. NeurIPS 2023Information Geometry of the Retinal Representation Manifold
  5. NeurIPS 2023Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
  6. NeurIPS 2023Inner Product-based Neural Network Similarity
  7. NeurIPS 2023Interpretable Graph Networks Formulate Universal Algebra Conjectures
  8. NeurIPS 2023Interpretable Prototype-based Graph Information Bottleneck
  9. NeurIPS 2023Investigating how ReLU-networks encode symmetries
  10. NeurIPS 2023Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
  11. NeurIPS 2023LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
  12. NeurIPS 2023Language Semantic Graph Guided Data-Efficient Learning
  13. NeurIPS 2023Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
  14. NeurIPS 2023Large sample spectral analysis of graph-based multi-manifold clustering
  15. NeurIPS 2023Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
  16. NeurIPS 2023Latent Graph Inference with Limited Supervision
  17. NeurIPS 2023Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs
  18. NeurIPS 2023LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings
  19. NeurIPS 2023Learning DAGs from Data with Few Root Causes
  20. NeurIPS 2023Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
  21. NeurIPS 2023Learning Invariant Representations of Graph Neural Networks via Cluster Generalization
  22. NeurIPS 2023Learning Large Graph Property Prediction via Graph Segment Training
  23. NeurIPS 2023Learning To Dive In Branch And Bound
  24. NeurIPS 2023Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets
  25. NeurIPS 2023Leveraging the two-timescale regime to demonstrate convergence of neural networks
  26. NeurIPS 2023Lie Point Symmetry and Physics-Informed Networks
  27. NeurIPS 2023Long Sequence Hopfield Memory
  28. NeurIPS 2023MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
  29. NeurIPS 2023MathNAS: If Blocks Have a Role in Mathematical Architecture Design
  30. NeurIPS 2023Maximum Independent Set: Self-Training through Dynamic Programming
  31. NeurIPS 2023MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy
  32. NeurIPS 2023Modulated Neural ODEs
  33. NeurIPS 2023Module-wise Training of Neural Networks via the Minimizing Movement Scheme
  34. NeurIPS 2023Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum
  35. NeurIPS 2023Multiplication-Free Transformer Training via Piecewise Affine Operations
  36. NeurIPS 2023MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
  37. NeurIPS 2023NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
  38. NeurIPS 2023NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks
  39. NeurIPS 2023Network Regression with Graph Laplacians
  40. NeurIPS 2023Neural (Tangent Kernel) Collapse
  41. NeurIPS 2023Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
  42. NeurIPS 2023Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity
  43. NeurIPS 2023Neural Functional Transformers
  44. NeurIPS 2023Neural Graph Generation from Graph Statistics
  45. NeurIPS 2023Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem
  46. NeurIPS 2023Neural Lyapunov Control for Discrete-Time Systems
  47. NeurIPS 2023Neural Oscillators are Universal
  48. NeurIPS 2023Neural Processes with Stability
  49. NeurIPS 2023Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
  50. NeurIPS 2023Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis

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