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 842 篇，第 15 / 17 页

  1. NeurIPS 2023Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning
  2. NeurIPS 2023Optimality of Message-Passing Architectures for Sparse Graphs
  3. NeurIPS 2023Optimization and Bayes: A Trade-off for Overparameterized Neural Networks
  4. NeurIPS 2023Outlier-Robust Gromov-Wasserstein for Graph Data
  5. NeurIPS 2023Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks
  6. NeurIPS 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
  7. NeurIPS 2023Penalising the biases in norm regularisation enforces sparsity
  8. NeurIPS 2023PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis
  9. NeurIPS 2023Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
  10. NeurIPS 2023Permutation Equivariant Neural Functionals
  11. NeurIPS 2023PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems
  12. NeurIPS 2023Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width
  13. NeurIPS 2023Polyhedron Attention Module: Learning Adaptive-order Interactions
  14. NeurIPS 2023Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
  15. NeurIPS 2023Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release
  16. NeurIPS 2023Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily
  17. NeurIPS 2023Probabilistic Invariant Learning with Randomized Linear Classifiers
  18. NeurIPS 2023Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantisation.
  19. NeurIPS 2023Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
  20. NeurIPS 2023Provable Guarantees for Neural Networks via Gradient Feature Learning
  21. NeurIPS 2023Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
  22. NeurIPS 2023Provable Training for Graph Contrastive Learning
  23. NeurIPS 2023Provably Bounding Neural Network Preimages
  24. NeurIPS 2023Pruning vs Quantization: Which is Better?
  25. NeurIPS 2023Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion
  26. NeurIPS 2023PyNeRF: Pyramidal Neural Radiance Fields
  27. NeurIPS 2023QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
  28. NeurIPS 2023QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution
  29. NeurIPS 2023Quasi-Monte Carlo Graph Random Features
  30. NeurIPS 2023Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks
  31. NeurIPS 2023Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
  32. NeurIPS 2023Recurrent Temporal Revision Graph Networks
  33. NeurIPS 2023Red Teaming Deep Neural Networks with Feature Synthesis Tools
  34. NeurIPS 2023Regularizing Neural Networks with Meta-Learning Generative Models
  35. NeurIPS 2023Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning
  36. NeurIPS 2023ResMem: Learn what you can and memorize the rest
  37. NeurIPS 2023Retaining Beneficial Information from Detrimental Data for Neural Network Repair
  38. NeurIPS 2023Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
  39. NeurIPS 2023Rethinking the Backward Propagation for Adversarial Transferability
  40. NeurIPS 2023Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
  41. NeurIPS 2023Reversible and irreversible bracket-based dynamics for deep graph neural networks
  42. NeurIPS 2023Riemannian Laplace approximations for Bayesian neural networks
  43. NeurIPS 2023Riemannian Residual Neural Networks
  44. NeurIPS 2023Robust low-rank training via approximate orthonormal constraints
  45. NeurIPS 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model
  46. NeurIPS 2023Robustness Guarantees for Adversarially Trained Neural Networks
  47. NeurIPS 2023Saddle-to-Saddle Dynamics in Diagonal Linear Networks
  48. NeurIPS 2023Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks
  49. NeurIPS 2023Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents
  50. NeurIPS 2023Scale Alone Does not Improve Mechanistic Interpretability in Vision Models

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