深度学习 · graph neural networks论文趋势 2023–2026

ICML/NeurIPS 深度学习方向：graph_neural_networks

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,648 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

深度学习 · graph neural networks论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20234896814823728
2024160517610297
2025915014115297
20261023216824326

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

全部深度学习 · graph neural networks论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 297 篇，第 4 / 6 页

  1. ICML 2025LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification
  2. ICML 2025Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
  3. ICML 2025ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive Learning
  4. ICML 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
  5. ICML 2025Multi-View Graph Clustering via Node-Guided Contrastive Encoding
  6. ICML 2025N2GON: Neural Networks for Graph-of-Net with Position Awareness
  7. ICML 2025No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
  8. ICML 2025Nonparametric Teaching for Graph Property Learners
  9. ICML 2025On Measuring Long-Range Interactions in Graph Neural Networks
  10. ICML 2025Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
  11. ICML 2025Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion Models
  12. ICML 2025PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities
  13. ICML 2025Position: Graph Matching Systems Deserve Better Benchmarks
  14. ICML 2025Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived
  15. ICML 2025Positional Encoding meets Persistent Homology on Graphs
  16. ICML 2025Primal-Dual Neural Algorithmic Reasoning
  17. ICML 2025Primphormer: Efficient Graph Transformers with Primal Representations
  18. ICML 2025Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
  19. ICML 2025Pruning for GNNs: Lower Complexity with Comparable Expressiveness
  20. ICML 2025Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs
  21. ICML 2025RelGNN: Composite Message Passing for Relational Deep Learning
  22. ICML 2025ResearchTown: Simulator of Human Research Community
  23. ICML 2025Rethinking Time Encoding via Learnable Transformation Functions
  24. ICML 2025Rhomboid Tiling for Geometric Graph Deep Learning
  25. ICML 2025SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
  26. ICML 2025Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation
  27. ICML 2025Scalable Sobolev IPM for Probability Measures on a Graph
  28. ICML 2025SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
  29. ICML 2025SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
  30. ICML 2025Signed Laplacians for Constrained Graph Clustering
  31. ICML 2025Simple Path Structural Encoding for Graph Transformers
  32. ICML 2025Smooth Interpolation for Improved Discrete Graph Generative Models
  33. ICML 2025SPHINX: Structural Prediction using Hypergraph Inference Network
  34. ICML 2025Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
  35. ICML 2025Stable Fair Graph Representation Learning with Lipschitz Constraint
  36. ICML 2025Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
  37. ICML 2025Supercharging Graph Transformers with Advective Diffusion
  38. ICML 2025Telling Peer Direct Effects from Indirect Effects in Observational Network Data
  39. ICML 2025Test-Time Graph Neural Dataset Search With Generative Projection
  40. ICML 2025The Generalized Skew Spectrum of Graphs
  41. ICML 2025The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
  42. ICML 2025Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks
  43. ICML 2025TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
  44. ICML 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
  45. ICML 2025Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph
  46. ICML 2025TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks
  47. ICML 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
  48. ICML 2025Towards characterizing the value of edge embeddings in Graph Neural Networks
  49. ICML 2025Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
  50. ICML 2025Unifews: You Need Fewer Operations for Efficient 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 查深度学习 · graph neural networks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": "dl-graph-neural-networks"}

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深度学习 · graph neural networks论文？
共 1,648 篇，按年份分别是 2023 年 728 篇、2024 年 297 篇、2025 年 297 篇、2026 年 326 篇。
NeurIPS 2026 有多少篇深度学习 · graph neural networks论文？
NeurIPS 2026 有 102 篇深度学习 · graph neural networks论文，上一届是 91 篇。
ICLR 2026 有多少篇深度学习 · graph neural networks论文？
ICLR 2026 有 32 篇深度学习 · graph neural networks论文，上一届是 50 篇。
ICML 2026 有多少篇深度学习 · graph neural networks论文？
ICML 2026 有 168 篇深度学习 · graph neural networks论文，上一届是 141 篇。
CVPR 2026 有多少篇深度学习 · graph neural networks论文？
CVPR 2026 有 24 篇深度学习 · graph neural networks论文，上一届是 15 篇。
哪个会议的深度学习 · graph neural networks论文最多？
NeurIPS，2023–2026 年共 842 篇。

「深度学习」下的其他主题