图神经网络论文趋势 2023–2026

主要结论

• 图神经网络论文从 2023 年的 434 篇降到 2026 年的 183 篇，热度在回落。
• NeurIPS 是发图神经网络论文最多的会议，2023–2026 年共 489 篇，占四个会议总量的 47%。
• 交叉方向里涨得最快的是数据集与基准：同时属于两个主题的论文从 2023 年的 10 篇增至 2026 年的 10 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的时间序列是 3.2 倍，图神经网络是 0.4 倍。

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

• NeurIPS 2026A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry
• ICML 2026Aitchison Embeddings for Learning Compositional Graph Representations
• ICLR 2026Certified Evaluation of Model-Level Explanations for Graph Neural Networks
• CVPR 2026Gamba Mamba-based graph convolutional network with dynamic graph topology learning
• NeurIPS 2025Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
• ICML 2025Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
• ICLR 2025Edge Prompt Tuning for Graph Neural Networks
• CVPR 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
• NeurIPS 2024[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"
• ICML 2024A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
• ICLR 2024Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
• CVPR 2024FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
• NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
• ICML 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
• ICLR 2023$\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks
• CVPR 2023Adversarially Robust Neural Architecture Search for Graph Neural Networks
• NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
• ICML 2026Any-dimensional invariant universality
• ICLR 2026Laplacian Kernelized Bandit
• CVPR 2026Global-Aware Edge Prioritization for Pose Graph Initialization

全部图神经网络论文

共 251 篇，第 1 / 6 页

1. NeurIPS 2023[Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification
2. NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
3. NeurIPS 2023[Re] Variational Neural Cellular Automata
4. NeurIPS 2023A Fractional Graph Laplacian Approach to Oversmoothing
5. NeurIPS 2023A graphon-signal analysis of graph neural networks
6. NeurIPS 2023A Metadata-Driven Approach to Understand Graph Neural Networks
7. NeurIPS 2023A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
8. NeurIPS 2023A new perspective on building efficient and expressive 3D equivariant graph neural networks
9. NeurIPS 2023A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation
10. NeurIPS 2023A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
11. NeurIPS 2023A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
12. NeurIPS 2023Accelerating Molecular Graph Neural Networks via Knowledge Distillation
13. NeurIPS 2023Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
14. NeurIPS 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
15. NeurIPS 2023Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
16. NeurIPS 2023Affinity-Aware Graph Networks
17. NeurIPS 2023AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity
18. NeurIPS 2023Analyzing Generalization of Neural Networks through Loss Path Kernels
19. NeurIPS 2023Approximately Equivariant Graph Networks
20. NeurIPS 2023Approximation-Generalization Trade-offs under (Approximate) Group Equivariance
21. NeurIPS 2023Are aligned neural networks adversarially aligned?
22. NeurIPS 2023Are GATs Out of Balance?
23. NeurIPS 2023ASPEN: Breaking Operator Barriers for Efficient Parallelization of Deep Neural Networks
24. NeurIPS 2023Asymmetric Certified Robustness via Feature-Convex Neural Networks
25. NeurIPS 2023AutoGO: Automated Computation Graph Optimization for Neural Network Evolution
26. NeurIPS 2023Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
27. NeurIPS 2023Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis
28. NeurIPS 2023Beyond probability partitions: Calibrating neural networks with semantic aware grouping
29. NeurIPS 2023Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing
30. NeurIPS 2023Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs
31. NeurIPS 2023Certifiably Robust Graph Contrastive Learning
32. NeurIPS 2023Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
33. NeurIPS 2023Cognitive Model Discovery via Disentangled RNNs
34. NeurIPS 2023Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections
35. NeurIPS 2023Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints
36. NeurIPS 2023Compression with Bayesian Implicit Neural Representations
37. NeurIPS 2023Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data
38. NeurIPS 2023Conformal Prediction for Time Series with Modern Hopfield Networks
39. NeurIPS 2023Contextual Gaussian Process Bandits with Neural Networks
40. NeurIPS 2023ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling
41. NeurIPS 2023Convergence of Actor-Critic with Multi-Layer Neural Networks
42. NeurIPS 2023CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics
43. NeurIPS 2023CosNet: A Generalized Spectral Kernel Network
44. NeurIPS 2023CP-SLAM: Collaborative Neural Point-based SLAM System
45. NeurIPS 2023Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective
46. NeurIPS 2023Crystal Structure Prediction by Joint Equivariant Diffusion
47. NeurIPS 2023Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
48. NeurIPS 2023D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion
49. NeurIPS 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment
50. NeurIPS 2023DeepPCR: Parallelizing Sequential Operations in Neural Networks

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。