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
- 深度学习 · graph neural networks论文从 2023 年的 728 篇降到 2026 年的 326 篇，热度在回落。
- NeurIPS 是发深度学习 · graph neural networks论文最多的会议，2023–2026 年共 842 篇，占四个会议总量的 51%。
- 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 9 篇增至 2026 年的 20 篇。
- 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 5；同组增长最快的扩散模型是 4.1 倍，深度学习 · graph neural networks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 | 489 | 68 | 148 | 23 | 728 |
| 2024 | 160 | 51 | 76 | 10 | 297 |
| 2025 | 91 | 50 | 141 | 15 | 297 |
| 2026 | 102 | 32 | 168 | 24 | 326 |
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 New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
- ICML 2026A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs
- ICLR 2026Laplacian Kernelized Bandit
- CVPR 2026Gamba Mamba-based graph convolutional network with dynamic graph topology learning
- NeurIPS 2025Depth-Width Tradeoffs for Transformers on Graph Tasks
- ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
- ICLR 2025Factor Graph-based Interpretable Neural Networks
- CVPR 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
- NeurIPS 2024[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
- ICML 2024A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
- ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
- CVPR 2024Learning Structure-from-Motion with Graph Attention Networks
- NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
- ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
- ICLR 2023Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
- CVPR 2023An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity
- NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
- ICML 2026A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
- ICLR 2026GTool: Graph Enhanced Tool Planning with Large Language Model
- CVPR 2026GSNR Graph Smooth Null-Space Representation for Inverse Problems
全部深度学习 · graph neural networks论文
共 326 篇，第 5 / 7 页
- ICML 2026Sparse Bayesian Deep Functional Learning with Structured Region Selection
- ICML 2026Spike-HTR: Spiking Neural Transformer for Handwritten Text Recognition
- ICML 2026ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
- ICML 2026Structure-Centric Graph Foundation Model via Geometric Bases
- ICML 2026Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental Learning
- ICML 2026SuperHype: Hypergraph Generation via Graph-Superposition Decomposition
- ICML 2026Supervised Graph Contrastive Learning for Gene Regulatory Networks
- ICML 2026SWING: Unlocking Implicit Graph Representations for Graph Random Features
- ICML 2026Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
- ICML 2026TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs
- ICML 2026Towards Generative Graph Matching for Graph Edit Distance Computation
- ICML 2026Towards Hierarchy–Uniformity Equilibrium: Recovering Semantic Depth in Hypergraph Contrastive Learning
- ICML 2026Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
- ICML 2026Uncertainty-Constrained Trustworthiness for Graph Learning
- ICML 2026Understanding Truncated Positional Encodings for Graph Neural Networks
- ICML 2026Unitary Convolutions for Message-passing and Positional Encodings on Directed Graphs
- ICML 2026VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
- ICML 2026Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
- ICML 2026View Space: Learning Representation across Arbitrary Graphs
- ICML 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
- ICML 2026What Makes a Desired Graph for Relational Deep Learning?
- ICML 2026When Do Graph Foundation Models Transfer? A Data-Centric Theory
- ICML 2026Which Algorithms Can Graph Neural Networks Learn?
- ICML 2026Why Are Linear RNNs More Parallelizable?
- NeurIPS 2026A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry
- NeurIPS 2026A Graph Foundation Model for Unified Clustering
- NeurIPS 2026A New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
- NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
- NeurIPS 2026A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
- NeurIPS 2026A2I: Adjacency-to-Image Structural Encodings for Graph Learning
- NeurIPS 2026Adaptive Feature Propagation for Attribute-Missing Graph Clustering
- NeurIPS 2026Adaptive Gated Simplicial Propagation for Node Classification in Multimodal Graphs
- NeurIPS 2026Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous Dynamics
- NeurIPS 2026Aggregation Dispersion: An Information-Geometric Diagnostic of Oversmoothing in Graph Neural Networks
- NeurIPS 2026Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
- NeurIPS 2026Avoiding Feature Collapse in Graph ODEs via Hysteretic Topology Evolution
- NeurIPS 2026B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
- NeurIPS 2026Benchmarking Graph Self-Supervised Learning for Node-Level Tasks: Insights and Strong Baseline
- NeurIPS 2026Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
- NeurIPS 2026Beyond Node Sequences: Relational Diffusion for Unified Graph Learning
- NeurIPS 2026Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
- NeurIPS 2026Biological Graph Priors Enable Representation Learning for Cellular Microscopy
- NeurIPS 2026Boosting Graph Contrastive Learning via Manifold-Guided Representation Disentanglement
- NeurIPS 2026Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein Distances
- NeurIPS 2026Caterpillar GNN: Replacing Message Passing with Graph-Level Aggregation
- NeurIPS 2026Chaining 2-FWL GNNs for Combinatorial Graph Alignment
- NeurIPS 2026CHORD: Cross-Model Hallucination Detection via Relational Graph Discrimination
- NeurIPS 2026CommunityKV: Efficient Long-Context Decoding via Graph Partitioning
- NeurIPS 2026Contractive Monoids: The Algebra Behind Stable Residual Propagation in Deep Graph Neural Networks
- NeurIPS 2026Contrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning
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"}
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
- 扩散模型 6,900
- 深度学习 · generative models and autoencoders 4,314
- 深度学习 · large language models 2,334
- 深度学习 · self supervised learning 1,958
- 深度学习 · optimization 953
- 深度学习 · representation learning 802
- 深度学习 · probabilistic methods 637
- 深度学习 · foundation models 536
- 深度学习 · causal inference 316
- 深度学习 · transfer learning 197