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 434 篇，第 4 / 9 页

151. ICML 2023MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods
152. ICML 2023Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
153. ICML 2023Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
154. ICML 2023Moccasin: Efficient Tensor Rematerialization for Neural Networks
155. ICML 2023Multi-class Graph Clustering via Approximated Effective $p$-Resistance
156. ICML 2023Neural networks trained with SGD learn distributions of increasing complexity
157. ICML 2023Neural signature kernels as infinite-width-depth-limits of controlled ResNets
158. ICML 2023Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks
159. ICML 2023Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks
160. ICML 2023On the Expressive Power of Geometric Graph Neural Networks
161. ICML 2023On the Initialization of Graph Neural Networks
162. ICML 2023Path Neural Networks: Expressive and Accurate Graph Neural Networks
163. ICML 2023Perturbation Analysis of Neural Collapse
164. ICML 2023Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision
165. ICML 2023Randomized Schur Complement Views for Graph Contrastive Learning
166. ICML 2023Relevant Walk Search for Explaining Graph Neural Networks
167. ICML 2023Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching
168. ICML 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networks
169. ICML 2023RGE: A Repulsive Graph Rectification for Node Classification via Influence
170. ICML 2023RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations
171. ICML 2023SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
172. ICML 2023SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge
173. ICML 2023Statistical Foundations of Prior-Data Fitted Networks
174. ICML 2023Taming graph kernels with random features
175. ICML 2023The Acquisition of Physical Knowledge in Generative Neural Networks
176. ICML 2023The Hessian perspective into the Nature of Convolutional Neural Networks
177. ICML 2023Total Variation Graph Neural Networks
178. ICML 2023Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
179. ICML 2023Towards Deep Attention in Graph Neural Networks: Problems and Remedies
180. ICML 2023Towards Understanding Generalization of Graph Neural Networks
181. ICML 2023Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data
182. ICML 2023Vertical Federated Graph Neural Network for Recommender System
183. ICML 2023XAI Beyond Classification: Interpretable Neural Clustering
184. NeurIPS 2023[Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification
185. NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
186. NeurIPS 2023[Re] Variational Neural Cellular Automata
187. NeurIPS 2023A Fractional Graph Laplacian Approach to Oversmoothing
188. NeurIPS 2023A graphon-signal analysis of graph neural networks
189. NeurIPS 2023A Metadata-Driven Approach to Understand Graph Neural Networks
190. NeurIPS 2023A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
191. NeurIPS 2023A new perspective on building efficient and expressive 3D equivariant graph neural networks
192. NeurIPS 2023A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation
193. NeurIPS 2023A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
194. NeurIPS 2023A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
195. NeurIPS 2023Accelerating Molecular Graph Neural Networks via Knowledge Distillation
196. NeurIPS 2023Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
197. NeurIPS 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
198. NeurIPS 2023Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
199. NeurIPS 2023Affinity-Aware Graph Networks
200. NeurIPS 2023AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity

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。