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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 251 | 69 | 96 | 18 | 434 |
| 2024 | 89 | 45 | 68 | 6 | 208 |
| 2025 | 75 | 45 | 81 | 12 | 213 |
| 2026 | 74 | 28 | 68 | 13 | 183 |
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 183 篇，第 4 / 4 页
- NeurIPS 2026Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
- NeurIPS 2026Invariant Hyperbolic Unfolding: Radial Canonicalization for Label-Free Cross-Graph Link Prediction
- NeurIPS 2026KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
- NeurIPS 2026Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
- NeurIPS 2026Long-Range Spatio-Temporal Graph Propagation Through Oscillations
- NeurIPS 2026MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
- NeurIPS 2026MIRAGE: Hierarchical MI-Surrogate Regulation for Graph Contrastive Learning
- NeurIPS 2026Multilateral Resistance-Guided Graph Message Passing for Trade Flow Prediction
- NeurIPS 2026Neighbor-Aware Snapshot-Based Temporal Graph Learning
- NeurIPS 2026Neural Networks With Dense Weights Are Not Universal Approximators
- NeurIPS 2026Neutral-atom quantum features as complementary structural encodings for graph learning
- NeurIPS 2026Normalized Architectures are Natively 4-Bit
- NeurIPS 2026OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
- NeurIPS 2026On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search
- NeurIPS 2026Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM
- NeurIPS 2026PATH: A Dual Perspective for High-quality Text-attributed Graph Learning
- NeurIPS 2026PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks
- NeurIPS 2026Pointwise Lipschitz Continuous Graph Algorithms
- NeurIPS 2026Practical Non-Stationary Graph Gaussian Processes
- NeurIPS 2026Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle
- NeurIPS 2026Robust Graph Diffusion Model
- NeurIPS 2026Robust Surrogate Modeling for Explainable Graph Neural Networks
- NeurIPS 2026Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
- NeurIPS 2026Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting
- NeurIPS 2026SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series Forecasting
- NeurIPS 2026SSDGExplainer: Structure-Semantic Dual-Guided Explainer for Graph Neural Networks
- NeurIPS 2026Toward in Silico Strain Evaluation: A Multimodal Surrogate for Fermentation Dynamics with Metabolic Graph Pretraining
- NeurIPS 2026Uncertainty-Aware Fuzzy Graph Contrastive Learning
- NeurIPS 2026WavCIL: Wavelet Coefficient-Domain Invariant Learning for Dynamic Graph OOD Generalization
- NeurIPS 2026Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
- NeurIPS 2026What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models
- NeurIPS 2026When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
- NeurIPS 2026When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees
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"}
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。